Merge branch 'linus' into x86/fixmap

Documentation/DocBook/kgdb.tmpl

@@ -84,10 +84,9 @@
     runs an instance of gdb against the vmlinux file which contains
     the symbols (not boot image such as bzImage, zImage, uImage...).
     In gdb the developer specifies the connection parameters and
-    connects to kgdb.  Depending on which kgdb I/O modules exist in
+    connects to kgdb.  The type of connection a developer makes with
-    the kernel for a given architecture, it may be possible to debug
+    gdb depends on the availability of kgdb I/O modules compiled as
-    the test machine's kernel with the development machine using a
+    builtin's or kernel modules in the test machine's kernel.
-    rs232 or ethernet connection.
     </para>
   </chapter>
   <chapter id="CompilingAKernel">
@@ -223,7 +222,7 @@
   </para>
   <para>
   IMPORTANT NOTE: Using this option with kgdb over the console
-  (kgdboc) or kgdb over ethernet (kgdboe) is not supported.
+  (kgdboc) is not supported.
   </para>
   </sect1>
   </chapter>
@@ -249,18 +248,11 @@
     (gdb) target remote /dev/ttyS0
     </programlisting>
     <para>
-    Example (kgdb to a terminal server):
+    Example (kgdb to a terminal server on tcp port 2012):
     </para>
     <programlisting>
     % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
+    (gdb) target remote 192.168.2.2:2012
-    </programlisting>
-    <para>
-    Example (kgdb over ethernet):
-    </para>
-    <programlisting>
-    % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
     </programlisting>
     <para>
     Once connected, you can debug a kernel the way you would debug an

Documentation/cpusets.txt

@@ -542,7 +542,7 @@ otherwise initial value -1 that indicates the cpuset has no request.
    2  : search cores in a package.
    3  : search cpus in a node [= system wide on non-NUMA system]
  ( 4  : search nodes in a chunk of node [on NUMA system] )
- ( 5~ : search system wide [on NUMA system])
+ ( 5  : search system wide [on NUMA system] )
 
 This file is per-cpuset and affect the sched domain where the cpuset
 belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset

Documentation/hwmon/sysfs-interface

@@ -2,17 +2,12 @@ Naming and data format standards for sysfs files
 ------------------------------------------------
 
 The libsensors library offers an interface to the raw sensors data
-through the sysfs interface. See libsensors documentation and source for
+through the sysfs interface. Since lm-sensors 3.0.0, libsensors is
-further information. As of writing this document, libsensors
+completely chip-independent. It assumes that all the kernel drivers
-(from lm_sensors 2.8.3) is heavily chip-dependent. Adding or updating
+implement the standard sysfs interface described in this document.
-support for any given chip requires modifying the library's code.
+This makes adding or updating support for any given chip very easy, as
-This is because libsensors was written for the procfs interface
+libsensors, and applications using it, do not need to be modified.
-older kernel modules were using, which wasn't standardized enough.
+This is a major improvement compared to lm-sensors 2.
-Recent versions of libsensors (from lm_sensors 2.8.2 and later) have
-support for the sysfs interface, though.
-
-The new sysfs interface was designed to be as chip-independent as
-possible.
 
 Note that motherboards vary widely in the connections to sensor chips.
 There is no standard that ensures, for example, that the second
@@ -35,19 +30,17 @@ access this data in a simple and consistent way. That said, such programs
 will have to implement conversion, labeling and hiding of inputs. For
 this reason, it is still not recommended to bypass the library.
 
-If you are developing a userspace application please send us feedback on
-this standard.
-
-Note that this standard isn't completely established yet, so it is subject
-to changes. If you are writing a new hardware monitoring driver those
-features can't seem to fit in this interface, please contact us with your
-extension proposal. Keep in mind that backward compatibility must be
-preserved.
-
 Each chip gets its own directory in the sysfs /sys/devices tree.  To
 find all sensor chips, it is easier to follow the device symlinks from
 /sys/class/hwmon/hwmon*.
 
+Up to lm-sensors 3.0.0, libsensors looks for hardware monitoring attributes
+in the "physical" device directory. Since lm-sensors 3.0.1, attributes found
+in the hwmon "class" device directory are also supported. Complex drivers
+(e.g. drivers for multifunction chips) may want to use this possibility to
+avoid namespace pollution. The only drawback will be that older versions of
+libsensors won't support the driver in question.
+
 All sysfs values are fixed point numbers.
 
 There is only one value per file, unlike the older /proc specification.

MAINTAINERS

@@ -4431,10 +4431,10 @@ M:	johnpol@2ka.mipt.ru
 S:	Maintained
 
 W83791D HARDWARE MONITORING DRIVER
-P:	Charles Spirakis
+P:	Marc Hulsman
-M:	bezaur@gmail.com
+M:	m.hulsman@tudelft.nl
 L:	lm-sensors@lm-sensors.org
-S:	Odd Fixes
+S:	Maintained
 
 W83793 HARDWARE MONITORING DRIVER
 P:	Rudolf Marek

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 26
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc8
 NAME = Rotary Wombat
 
 # *DOCUMENTATION*

arch/alpha/Makefile

@@ -13,6 +13,7 @@ NM := $(NM) -B
 LDFLAGS_vmlinux	:= -static -N #-relax
 CHECKFLAGS	+= -D__alpha__ -m64
 cflags-y	:= -pipe -mno-fp-regs -ffixed-8 -msmall-data
+cflags-y	+= $(call cc-option, -fno-jump-tables)
 
 cpuflags-$(CONFIG_ALPHA_EV4)		:= -mcpu=ev4
 cpuflags-$(CONFIG_ALPHA_EV5)		:= -mcpu=ev5

arch/alpha/kernel/core_t2.c

@@ -74,6 +74,8 @@
 # define DBG(args)
 #endif
 
+DEFINE_SPINLOCK(t2_hae_lock);
+
 static volatile unsigned int t2_mcheck_any_expected;
 static volatile unsigned int t2_mcheck_last_taken;
 

arch/alpha/kernel/pci.c

@@ -71,6 +71,23 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82378, quirk_i
 static void __init
 quirk_cypress(struct pci_dev *dev)
 {
+	/* The Notorious Cy82C693 chip.  */
+
+	/* The generic legacy mode IDE fixup in drivers/pci/probe.c
+	   doesn't work correctly with the Cypress IDE controller as
+	   it has non-standard register layout.  Fix that.  */
+	if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE) {
+		dev->resource[2].start = dev->resource[3].start = 0;
+		dev->resource[2].end = dev->resource[3].end = 0;
+		dev->resource[2].flags = dev->resource[3].flags = 0;
+		if (PCI_FUNC(dev->devfn) == 2) {
+			dev->resource[0].start = 0x170;
+			dev->resource[0].end = 0x177;
+			dev->resource[1].start = 0x376;
+			dev->resource[1].end = 0x376;
+		}
+	}
+
 	/* The Cypress bridge responds on the PCI bus in the address range
 	   0xffff0000-0xffffffff (conventional x86 BIOS ROM).  There is no
 	   way to turn this off.  The bridge also supports several extended

arch/alpha/kernel/traps.c

@@ -447,7 +447,7 @@ struct unaligned_stat {
 
 
 /* Macro for exception fixup code to access integer registers.  */
-#define una_reg(r)  (regs->regs[(r) >= 16 && (r) <= 18 ? (r)+19 : (r)])
+#define una_reg(r)  (_regs[(r) >= 16 && (r) <= 18 ? (r)+19 : (r)])
 
 
 asmlinkage void
@@ -456,6 +456,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 {
 	long error, tmp1, tmp2, tmp3, tmp4;
 	unsigned long pc = regs->pc - 4;
+	unsigned long *_regs = regs->regs;
 	const struct exception_table_entry *fixup;
 
 	unaligned[0].count++;

arch/ia64/kernel/iosapic.c

@@ -558,8 +558,6 @@ static struct iosapic_rte_info * __init_refok iosapic_alloc_rte (void)
 	if (!iosapic_kmalloc_ok && list_empty(&free_rte_list)) {
 		rte = alloc_bootmem(sizeof(struct iosapic_rte_info) *
 				    NR_PREALLOCATE_RTE_ENTRIES);
-		if (!rte)
-			return NULL;
 		for (i = 0; i < NR_PREALLOCATE_RTE_ENTRIES; i++, rte++)
 			list_add(&rte->rte_list, &free_rte_list);
 	}

arch/ia64/kernel/setup.c

@@ -578,8 +578,6 @@ setup_arch (char **cmdline_p)
 	cpu_init();	/* initialize the bootstrap CPU */
 	mmu_context_init();	/* initialize context_id bitmap */
 
-	check_sal_cache_flush();
-
 #ifdef CONFIG_ACPI
 	acpi_boot_init();
 #endif
@@ -607,6 +605,7 @@ setup_arch (char **cmdline_p)
 		ia64_mca_init();
 
 	platform_setup(cmdline_p);
+	check_sal_cache_flush();
 	paging_init();
 }
 

arch/ia64/sn/kernel/sn2/sn2_smp.c

@@ -512,6 +512,8 @@ static ssize_t sn2_ptc_proc_write(struct file *file, const char __user *user, si
 	int cpu;
 	char optstr[64];
 
+	if (count == 0 || count > sizeof(optstr))
+		return -EINVAL;
 	if (copy_from_user(optstr, user, count))
 		return -EFAULT;
 	optstr[count - 1] = '\0';

arch/powerpc/kernel/vdso.c

@@ -142,7 +142,7 @@ static void dump_one_vdso_page(struct page *pg, struct page *upg)
 	printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
 	       page_count(pg),
 	       pg->flags);
-	if (upg/* && pg != upg*/) {
+	if (upg && !IS_ERR(upg) /* && pg != upg*/) {
 		printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
 						       << PAGE_SHIFT),
 		       page_count(upg),

arch/x86/Kconfig

@@ -383,6 +383,7 @@ config VMI
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
+	select PARAVIRT_CLOCK
 	depends on !(X86_VISWS || X86_VOYAGER)
 	help
 	  Turning on this option will allow you to run a paravirtualized clock
@@ -410,6 +411,10 @@ config PARAVIRT
 	  over full virtualization.  However, when run without a hypervisor
 	  the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_CLOCK
+	bool
+	default n
+
 endif
 
 config MEMTEST_BOOTPARAM

arch/x86/kernel/Makefile

@@ -82,6 +82,7 @@ obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 

arch/x86/kernel/geode_32.c

@@ -166,6 +166,8 @@ int geode_has_vsa2(void)
 	static int has_vsa2 = -1;
 
 	if (has_vsa2 == -1) {
+		u16 val;
+
 		/*
 		 * The VSA has virtual registers that we can query for a
 		 * signature.
@@ -173,7 +175,8 @@ int geode_has_vsa2(void)
 		outw(VSA_VR_UNLOCK, VSA_VRC_INDEX);
 		outw(VSA_VR_SIGNATURE, VSA_VRC_INDEX);
 
-		has_vsa2 = (inw(VSA_VRC_DATA) == VSA_SIG);
+		val = inw(VSA_VRC_DATA);
+		has_vsa2 = (val == AMD_VSA_SIG || val == GSW_VSA_SIG);
 	}
 
 	return has_vsa2;

arch/x86/kernel/kvmclock.c

@@ -18,6 +18,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/kvm_para.h>
+#include <asm/pvclock.h>
 #include <asm/arch_hooks.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
@@ -36,18 +37,9 @@ static int parse_no_kvmclock(char *arg)
 early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
-#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+static struct pvclock_wall_clock wall_clock;
 
-static inline u64 kvm_get_delta(u64 last_tsc)
-{
-	int cpu = smp_processor_id();
-	u64 delta = native_read_tsc() - last_tsc;
-	return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
-}
-
-static struct kvm_wall_clock wall_clock;
-static cycle_t kvm_clock_read(void);
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for
@@ -55,64 +47,37 @@ static cycle_t kvm_clock_read(void);
  */
 static unsigned long kvm_get_wallclock(void)
 {
-	u32 wc_sec, wc_nsec;
+	struct pvclock_vcpu_time_info *vcpu_time;
-	u64 delta;
 	struct timespec ts;
-	int version, nsec;
 	int low, high;
 
 	low = (int)__pa(&wall_clock);
 	high = ((u64)__pa(&wall_clock) >> 32);
-
-	delta = kvm_clock_read();
-
 	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
-	do {
-		version = wall_clock.wc_version;
-		rmb();
-		wc_sec = wall_clock.wc_sec;
-		wc_nsec = wall_clock.wc_nsec;
-		rmb();
-	} while ((wall_clock.wc_version != version) || (version & 1));
 
-	delta = kvm_clock_read() - delta;
+	vcpu_time = &get_cpu_var(hv_clock);
-	delta += wc_nsec;
+	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
-	nsec = do_div(delta, NSEC_PER_SEC);
+	put_cpu_var(hv_clock);
-	set_normalized_timespec(&ts, wc_sec + delta, nsec);
+
-	/*
+	return ts.tv_sec;
-	 * Of all mechanisms of time adjustment I've tested, this one
-	 * was the champion!
-	 */
-	return ts.tv_sec + 1;
 }
 
 static int kvm_set_wallclock(unsigned long now)
 {
-	return 0;
+	return -1;
 }
 
-/*
- * This is our read_clock function. The host puts an tsc timestamp each time
- * it updates a new time. Without the tsc adjustment, we can have a situation
- * in which a vcpu starts to run earlier (smaller system_time), but probes
- * time later (compared to another vcpu), leading to backwards time
- */
 static cycle_t kvm_clock_read(void)
 {
-	u64 last_tsc, now;
+	struct pvclock_vcpu_time_info *src;
-	int cpu;
+	cycle_t ret;
 
-	preempt_disable();
+	src = &get_cpu_var(hv_clock);
-	cpu = smp_processor_id();
+	ret = pvclock_clocksource_read(src);
-
+	put_cpu_var(hv_clock);
-	last_tsc = get_clock(cpu, tsc_timestamp);
+	return ret;
-	now = get_clock(cpu, system_time);
-
-	now += kvm_get_delta(last_tsc);
-	preempt_enable();
-
-	return now;
 }
+
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
 	.read = kvm_clock_read,
@@ -123,13 +88,14 @@ static struct clocksource kvm_clock = {
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int kvm_register_clock(void)
+static int kvm_register_clock(char *txt)
 {
 	int cpu = smp_processor_id();
 	int low, high;
 	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
 	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
-
+	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
+	       cpu, high, low, txt);
 	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
 }
 
@@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void)
 	 * Now that the first cpu already had this clocksource initialized,
 	 * we shouldn't fail.
 	 */
-	WARN_ON(kvm_register_clock());
+	WARN_ON(kvm_register_clock("secondary cpu clock"));
 	/* ok, done with our trickery, call native */
 	setup_secondary_APIC_clock();
 }
 #endif
 
+#ifdef CONFIG_SMP
+void __init kvm_smp_prepare_boot_cpu(void)
+{
+	WARN_ON(kvm_register_clock("primary cpu clock"));
+	native_smp_prepare_boot_cpu();
+}
+#endif
+
 /*
  * After the clock is registered, the host will keep writing to the
  * registered memory location. If the guest happens to shutdown, this memory
@@ -174,13 +148,16 @@ void __init kvmclock_init(void)
 		return;
 
 	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-		if (kvm_register_clock())
+		if (kvm_register_clock("boot clock"))
 			return;
 		pv_time_ops.get_wallclock = kvm_get_wallclock;
 		pv_time_ops.set_wallclock = kvm_set_wallclock;
 		pv_time_ops.sched_clock = kvm_clock_read;
 #ifdef CONFIG_X86_LOCAL_APIC
 		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+#endif
+#ifdef CONFIG_SMP
+		smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
 		machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC

arch/x86/kernel/process_32.c

@@ -333,6 +333,7 @@ void flush_thread(void)
 	/*
 	 * Forget coprocessor state..
 	 */
+	tsk->fpu_counter = 0;
 	clear_fpu(tsk);
 	clear_used_math();
 }

arch/x86/kernel/process_64.c

@@ -294,6 +294,7 @@ void flush_thread(void)
 	/*
 	 * Forget coprocessor state..
 	 */
+	tsk->fpu_counter = 0;
 	clear_fpu(tsk);
 	clear_used_math();
 }

arch/x86/kernel/pvclock.c

@@ -0,0 +1,141 @@
+/*  paravirtual clock -- common code used by kvm/xen
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+*/
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <asm/pvclock.h>
+
+/*
+ * These are perodically updated
+ *    xen: magic shared_info page
+ *    kvm: gpa registered via msr
+ * and then copied here.
+ */
+struct pvclock_shadow_time {
+	u64 tsc_timestamp;     /* TSC at last update of time vals.  */
+	u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
+	u32 tsc_to_nsec_mul;
+	int tsc_shift;
+	u32 version;
+};
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+	u64 product;
+#ifdef __i386__
+	u32 tmp1, tmp2;
+#endif
+
+	if (shift < 0)
+		delta >>= -shift;
+	else
+		delta <<= shift;
+
+#ifdef __i386__
+	__asm__ (
+		"mul  %5       ; "
+		"mov  %4,%%eax ; "
+		"mov  %%edx,%4 ; "
+		"mul  %5       ; "
+		"xor  %5,%5    ; "
+		"add  %4,%%eax ; "
+		"adc  %5,%%edx ; "
+		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
+		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif __x86_64__
+	__asm__ (
+		"mul %%rdx ; shrd $32,%%rdx,%%rax"
+		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+#else
+#error implement me!
+#endif
+
+	return product;
+}
+
+static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
+{
+	u64 delta = native_read_tsc() - shadow->tsc_timestamp;
+	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
+}
+
+/*
+ * Reads a consistent set of time-base values from hypervisor,
+ * into a shadow data area.
+ */
+static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
+					struct pvclock_vcpu_time_info *src)
+{
+	do {
+		dst->version = src->version;
+		rmb();		/* fetch version before data */
+		dst->tsc_timestamp     = src->tsc_timestamp;
+		dst->system_timestamp  = src->system_time;
+		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
+		dst->tsc_shift         = src->tsc_shift;
+		rmb();		/* test version after fetching data */
+	} while ((src->version & 1) || (dst->version != src->version));
+
+	return dst->version;
+}
+
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+	struct pvclock_shadow_time shadow;
+	unsigned version;
+	cycle_t ret, offset;
+
+	do {
+		version = pvclock_get_time_values(&shadow, src);
+		barrier();
+		offset = pvclock_get_nsec_offset(&shadow);
+		ret = shadow.system_timestamp + offset;
+		barrier();
+	} while (version != src->version);
+
+	return ret;
+}
+
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
+			    struct pvclock_vcpu_time_info *vcpu_time,
+			    struct timespec *ts)
+{
+	u32 version;
+	u64 delta;
+	struct timespec now;
+
+	/* get wallclock at system boot */
+	do {
+		version = wall_clock->version;
+		rmb();		/* fetch version before time */
+		now.tv_sec  = wall_clock->sec;
+		now.tv_nsec = wall_clock->nsec;
+		rmb();		/* fetch time before checking version */
+	} while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+	delta = pvclock_clocksource_read(vcpu_time);	/* time since system boot */
+	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+
+	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
+	now.tv_sec = delta;
+
+	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+}

arch/x86/kernel/setup_32.c

@@ -532,10 +532,16 @@ static void __init reserve_crashkernel(void)
 					(unsigned long)(crash_size >> 20),
 					(unsigned long)(crash_base >> 20),
 					(unsigned long)(total_mem >> 20));
+
+			if (reserve_bootmem(crash_base, crash_size,
+					BOOTMEM_EXCLUSIVE) < 0) {
+				printk(KERN_INFO "crashkernel reservation "
+					"failed - memory is in use\n");
+				return;
+			}
+
 			crashk_res.start = crash_base;
 			crashk_res.end   = crash_base + crash_size - 1;
-			reserve_bootmem(crash_base, crash_size,
-					BOOTMEM_DEFAULT);
 		} else
 			printk(KERN_INFO "crashkernel reservation failed - "
 					"you have to specify a base address\n");

arch/x86/kernel/tsc_32.c

@@ -14,7 +14,10 @@
 
 #include "mach_timer.h"
 
-static int tsc_disabled;
+/* native_sched_clock() is called before tsc_init(), so
+   we must start with the TSC soft disabled to prevent
+   erroneous rdtsc usage on !cpu_has_tsc processors */
+static int tsc_disabled = -1;
 
 /*
  * On some systems the TSC frequency does not
@@ -402,25 +405,20 @@ void __init tsc_init(void)
 {
 	int cpu;
 
-	if (!cpu_has_tsc || tsc_disabled) {
+	if (!cpu_has_tsc || tsc_disabled > 0)
-		/* Disable the TSC in case of !cpu_has_tsc */
-		tsc_disabled = 1;
 		return;
-	}
 
 	cpu_khz = calculate_cpu_khz();
 	tsc_khz = cpu_khz;
 
 	if (!cpu_khz) {
 		mark_tsc_unstable("could not calculate TSC khz");
-		/*
-		 * We need to disable the TSC completely in this case
-		 * to prevent sched_clock() from using it.
-		 */
-		tsc_disabled = 1;
 		return;
 	}
 
+	/* now allow native_sched_clock() to use rdtsc */
+	tsc_disabled = 0;
+
 	printk("Detected %lu.%03lu MHz processor.\n",
 				(unsigned long)cpu_khz / 1000,
 				(unsigned long)cpu_khz % 1000);

arch/x86/kvm/i8254.c

@@ -200,10 +200,13 @@ int __pit_timer_fn(struct kvm_kpit_state *ps)
 
 	atomic_inc(&pt->pending);
 	smp_mb__after_atomic_inc();
-	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
+	if (vcpu0) {
+		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
+		if (waitqueue_active(&vcpu0->wq)) {
 			vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 			wake_up_interruptible(&vcpu0->wq);
 		}
+	}
 
 	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);
 	pt->scheduled = ktime_to_ns(pt->timer.expires);

arch/x86/kvm/lapic.c

@@ -940,6 +940,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 	wait_queue_head_t *q = &apic->vcpu->wq;
 
 	atomic_inc(&apic->timer.pending);
+	set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
 	if (waitqueue_active(q)) {
 		apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(q);

arch/x86/kvm/mmu.c

@@ -640,6 +640,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
 			rmap_remove(kvm, spte);
 			--kvm->stat.lpages;
 			set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+			spte = NULL;
 			write_protected = 1;
 		}
 		spte = rmap_next(kvm, rmapp, spte);
@@ -1082,10 +1083,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		struct kvm_mmu_page *shadow;
 
 		spte |= PT_WRITABLE_MASK;
-		if (user_fault) {
-			mmu_unshadow(vcpu->kvm, gfn);
-			goto unshadowed;
-		}
 
 		shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
 		if (shadow ||
@@ -1102,8 +1099,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		}
 	}
 
-unshadowed:
-
 	if (pte_access & ACC_WRITE_MASK)
 		mark_page_dirty(vcpu->kvm, gfn);
 
@@ -1580,11 +1575,13 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
 				  u64 *spte,
 				  const void *new)
 {
-	if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
+	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
-	    && !vcpu->arch.update_pte.largepage) {
+		if (!vcpu->arch.update_pte.largepage ||
+		    sp->role.glevels == PT32_ROOT_LEVEL) {
 			++vcpu->kvm->stat.mmu_pde_zapped;
 			return;
 		}
+        }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
 	if (sp->role.glevels == PT32_ROOT_LEVEL)

arch/x86/kvm/vmx.c

@@ -566,7 +566,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	load_transition_efer(vmx);
 }
 
-static void vmx_load_host_state(struct vcpu_vmx *vmx)
+static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 {
 	unsigned long flags;
 
@@ -596,6 +596,13 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx)
 	reload_host_efer(vmx);
 }
 
+static void vmx_load_host_state(struct vcpu_vmx *vmx)
+{
+	preempt_disable();
+	__vmx_load_host_state(vmx);
+	preempt_enable();
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
@@ -654,7 +661,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	vmx_load_host_state(to_vmx(vcpu));
+	__vmx_load_host_state(to_vmx(vcpu));
 }
 
 static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
@@ -884,11 +891,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 	switch (msr_index) {
 #ifdef CONFIG_X86_64
 	case MSR_EFER:
+		vmx_load_host_state(vmx);
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
-		if (vmx->host_state.loaded) {
-			reload_host_efer(vmx);
-			load_transition_efer(vmx);
-		}
 		break;
 	case MSR_FS_BASE:
 		vmcs_writel(GUEST_FS_BASE, data);
@@ -910,11 +914,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		guest_write_tsc(data);
 		break;
 	default:
+		vmx_load_host_state(vmx);
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
-			if (vmx->host_state.loaded)
-				load_msrs(vmx->guest_msrs, vmx->save_nmsrs);
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);

arch/x86/kvm/x86.c

@@ -492,8 +492,8 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
 	static int version;
-	struct kvm_wall_clock wc;
+	struct pvclock_wall_clock wc;
-	struct timespec wc_ts;
+	struct timespec now, sys, boot;
 
 	if (!wall_clock)
 		return;
@@ -502,10 +502,19 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 
-	wc_ts = current_kernel_time();
+	/*
-	wc.wc_sec = wc_ts.tv_sec;
+	 * The guest calculates current wall clock time by adding
-	wc.wc_nsec = wc_ts.tv_nsec;
+	 * system time (updated by kvm_write_guest_time below) to the
-	wc.wc_version = version;
+	 * wall clock specified here.  guest system time equals host
+	 * system time for us, thus we must fill in host boot time here.
+	 */
+	now = current_kernel_time();
+	ktime_get_ts(&sys);
+	boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+
+	wc.sec = boot.tv_sec;
+	wc.nsec = boot.tv_nsec;
+	wc.version = version;
 
 	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
 
@@ -513,6 +522,45 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 }
 
+static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
+{
+	uint32_t quotient, remainder;
+
+	/* Don't try to replace with do_div(), this one calculates
+	 * "(dividend << 32) / divisor" */
+	__asm__ ( "divl %4"
+		  : "=a" (quotient), "=d" (remainder)
+		  : "0" (0), "1" (dividend), "r" (divisor) );
+	return quotient;
+}
+
+static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+{
+	uint64_t nsecs = 1000000000LL;
+	int32_t  shift = 0;
+	uint64_t tps64;
+	uint32_t tps32;
+
+	tps64 = tsc_khz * 1000LL;
+	while (tps64 > nsecs*2) {
+		tps64 >>= 1;
+		shift--;
+	}
+
+	tps32 = (uint32_t)tps64;
+	while (tps32 <= (uint32_t)nsecs) {
+		tps32 <<= 1;
+		shift++;
+	}
+
+	hv_clock->tsc_shift = shift;
+	hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+
+	pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
+		 __FUNCTION__, tsc_khz, hv_clock->tsc_shift,
+		 hv_clock->tsc_to_system_mul);
+}
+
 static void kvm_write_guest_time(struct kvm_vcpu *v)
 {
 	struct timespec ts;
@@ -523,6 +571,11 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	if ((!vcpu->time_page))
 		return;
 
+	if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
+		kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
+		vcpu->hv_clock_tsc_khz = tsc_khz;
+	}
+
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
 	kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
@@ -537,9 +590,9 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	/*
 	 * The interface expects us to write an even number signaling that the
 	 * update is finished. Since the guest won't see the intermediate
-	 * state, we just write "2" at the end
+	 * state, we just increase by 2 at the end.
 	 */
-	vcpu->hv_clock.version = 2;
+	vcpu->hv_clock.version += 2;
 
 	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
 
@@ -599,10 +652,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		/* ...but clean it before doing the actual write */
 		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
 
-		vcpu->arch.hv_clock.tsc_to_system_mul =
-					clocksource_khz2mult(tsc_khz, 22);
-		vcpu->arch.hv_clock.tsc_shift = 22;
-
 		down_read(&current->mm->mmap_sem);
 		vcpu->arch.time_page =
 				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
@@ -2759,6 +2808,8 @@ again:
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
 			__kvm_migrate_timers(vcpu);
+		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+			kvm_x86_ops->tlb_flush(vcpu);
 		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
 				       &vcpu->requests)) {
 			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -2772,6 +2823,7 @@ again:
 		}
 	}
 
+	clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
 	kvm_inject_pending_timer_irqs(vcpu);
 
 	preempt_disable();
@@ -2781,15 +2833,7 @@ again:
 
 	local_irq_disable();
 
-	if (need_resched()) {
+	if (vcpu->requests || need_resched()) {
-		local_irq_enable();
-		preempt_enable();
-		r = 1;
-		goto out;
-	}
-
-	if (vcpu->requests)
-		if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
 		local_irq_enable();
 		preempt_enable();
 		r = 1;
@@ -2825,9 +2869,6 @@ again:
 
 	kvm_guest_enter();
 
-	if (vcpu->requests)
-		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
-			kvm_x86_ops->tlb_flush(vcpu);
 
 	KVMTRACE_0D(VMENTRY, vcpu, entryexit);
 	kvm_x86_ops->run(vcpu, kvm_run);

arch/x86/xen/Kconfig

@@ -5,8 +5,9 @@
 config XEN
 	bool "Xen guest support"
 	select PARAVIRT
+	select PARAVIRT_CLOCK
 	depends on X86_32
-	depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
+	depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER)
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the

arch/x86/xen/enlighten.c

@@ -785,20 +785,18 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
 static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 	pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
+	int i;
 
 	/* special set_pte for pagetable initialization */
 	pv_mmu_ops.set_pte = xen_set_pte_init;
 
 	init_mm.pgd = base;
 	/*
-	 * copy top-level of Xen-supplied pagetable into place.	 For
+	 * copy top-level of Xen-supplied pagetable into place.  This
-	 * !PAE we can use this as-is, but for PAE it is a stand-in
+	 * is a stand-in while we copy the pmd pages.
-	 * while we copy the pmd pages.
 	 */
 	memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
-	if (PTRS_PER_PMD > 1) {
-		int i;
 	/*
 	 * For PAE, need to allocate new pmds, rather than
 	 * share Xen's, since Xen doesn't like pmd's being
@@ -817,7 +815,6 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 		} else
 			pgd_clear(&base[i]);
 	}
-	}
 
 	/* make sure zero_page is mapped RO so we can use it in pagetables */
 	make_lowmem_page_readonly(empty_zero_page);
@@ -873,17 +870,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 
 	/* Actually pin the pagetable down, but we can't set PG_pinned
 	   yet because the page structures don't exist yet. */
-	{
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
-		unsigned level;
-
-#ifdef CONFIG_X86_PAE
-		level = MMUEXT_PIN_L3_TABLE;
-#else
-		level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-		pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
-	}
 }
 
 /* This is called once we have the cpu_possible_map */
@@ -1120,7 +1107,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.make_pte = xen_make_pte,
 	.make_pgd = xen_make_pgd,
 
-#ifdef CONFIG_X86_PAE
 	.set_pte_atomic = xen_set_pte_atomic,
 	.set_pte_present = xen_set_pte_at,
 	.set_pud = xen_set_pud,
@@ -1129,7 +1115,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.make_pmd = xen_make_pmd,
 	.pmd_val = xen_pmd_val,
-#endif	/* PAE */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
@@ -1257,6 +1242,11 @@ asmlinkage void __init xen_start_kernel(void)
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
 		pv_info.kernel_rpl = 0;
 
+	/* Prevent unwanted bits from being set in PTEs. */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	if (!is_initial_xendomain())
+		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
 	/* set the limit of our address space */
 	xen_reserve_top();
 

arch/x86/xen/mmu.c

@@ -179,50 +179,56 @@ out:
 		preempt_enable();
 }
 
+/* Assume pteval_t is equivalent to all the other *val_t types. */
+static pteval_t pte_mfn_to_pfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
+static pteval_t pte_pfn_to_mfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
 pteval_t xen_pte_val(pte_t pte)
 {
-	pteval_t ret = pte.pte;
+	return pte_mfn_to_pfn(pte.pte);
-
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-
-	return ret;
 }
 
 pgdval_t xen_pgd_val(pgd_t pgd)
 {
-	pgdval_t ret = pgd.pgd;
+	return pte_mfn_to_pfn(pgd.pgd);
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
 }
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	if (pte & _PAGE_PRESENT) {
+	pte = pte_pfn_to_mfn(pte);
-		pte = phys_to_machine(XPADDR(pte)).maddr;
+	return native_make_pte(pte);
-		pte &= ~(_PAGE_PCD | _PAGE_PWT);
-	}
-
-	return (pte_t){ .pte = pte };
 }
 
 pgd_t xen_make_pgd(pgdval_t pgd)
 {
-	if (pgd & _PAGE_PRESENT)
+	pgd = pte_pfn_to_mfn(pgd);
-		pgd = phys_to_machine(XPADDR(pgd)).maddr;
+	return native_make_pgd(pgd);
-
-	return (pgd_t){ pgd };
 }
 
 pmdval_t xen_pmd_val(pmd_t pmd)
 {
-	pmdval_t ret = native_pmd_val(pmd);
+	return pte_mfn_to_pfn(pmd.pmd);
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
 }
-#ifdef CONFIG_X86_PAE
+
 void xen_set_pud(pud_t *ptr, pud_t val)
 {
 	struct multicall_space mcs;
@@ -267,17 +273,9 @@ void xen_pmd_clear(pmd_t *pmdp)
 
 pmd_t xen_make_pmd(pmdval_t pmd)
 {
-	if (pmd & _PAGE_PRESENT)
+	pmd = pte_pfn_to_mfn(pmd);
-		pmd = phys_to_machine(XPADDR(pmd)).maddr;
-
 	return native_make_pmd(pmd);
 }
-#else  /* !PAE */
-void xen_set_pte(pte_t *ptep, pte_t pte)
-{
-	*ptep = pte;
-}
-#endif	/* CONFIG_X86_PAE */
 
 /*
   (Yet another) pagetable walker.  This one is intended for pinning a
@@ -430,8 +428,6 @@ static int pin_page(struct page *page, enum pt_level level)
    read-only, and can be pinned. */
 void xen_pgd_pin(pgd_t *pgd)
 {
-	unsigned level;
-
 	xen_mc_batch();
 
 	if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
@@ -441,14 +437,7 @@ void xen_pgd_pin(pgd_t *pgd)
 		xen_mc_batch();
 	}
 
-#ifdef CONFIG_X86_PAE
+	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
-	level = MMUEXT_PIN_L3_TABLE;
-#else
-	level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-	xen_do_pin(level, PFN_DOWN(__pa(pgd)));
-
 	xen_mc_issue(0);
 }
 

arch/x86/xen/mmu.h

@@ -37,14 +37,13 @@ void xen_exit_mmap(struct mm_struct *mm);
 void xen_pgd_pin(pgd_t *pgd);
 //void xen_pgd_unpin(pgd_t *pgd);
 
-#ifdef CONFIG_X86_PAE
+pteval_t xen_pte_val(pte_t);
-unsigned long long xen_pte_val(pte_t);
+pmdval_t xen_pmd_val(pmd_t);
-unsigned long long xen_pmd_val(pmd_t);
+pgdval_t xen_pgd_val(pgd_t);
-unsigned long long xen_pgd_val(pgd_t);
 
-pte_t xen_make_pte(unsigned long long);
+pte_t xen_make_pte(pteval_t);
-pmd_t xen_make_pmd(unsigned long long);
+pmd_t xen_make_pmd(pmdval_t);
-pgd_t xen_make_pgd(unsigned long long);
+pgd_t xen_make_pgd(pgdval_t);
 
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval);
@@ -53,15 +52,4 @@ void xen_set_pud(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
-
-#else
-unsigned long xen_pte_val(pte_t);
-unsigned long xen_pmd_val(pmd_t);
-unsigned long xen_pgd_val(pgd_t);
-
-pte_t xen_make_pte(unsigned long);
-pmd_t xen_make_pmd(unsigned long);
-pgd_t xen_make_pgd(unsigned long);
-#endif
-
 #endif	/* _XEN_MMU_H */

arch/x86/xen/time.c

@@ -14,6 +14,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
 
+#include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -31,17 +32,6 @@
 
 static cycle_t xen_clocksource_read(void);
 
-/* These are perodically updated in shared_info, and then copied here. */
-struct shadow_time_info {
-	u64 tsc_timestamp;     /* TSC at last update of time vals.  */
-	u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
-	u32 tsc_to_nsec_mul;
-	int tsc_shift;
-	u32 version;
-};
-
-static DEFINE_PER_CPU(struct shadow_time_info, shadow_time);
-
 /* runstate info updated by Xen */
 static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
 
@@ -211,7 +201,7 @@ unsigned long long xen_sched_clock(void)
 unsigned long xen_cpu_khz(void)
 {
 	u64 xen_khz = 1000000ULL << 32;
-	const struct vcpu_time_info *info =
+	const struct pvclock_vcpu_time_info *info =
 		&HYPERVISOR_shared_info->vcpu_info[0].time;
 
 	do_div(xen_khz, info->tsc_to_system_mul);
@@ -223,121 +213,26 @@ unsigned long xen_cpu_khz(void)
 	return xen_khz;
 }
 
-/*
- * Reads a consistent set of time-base values from Xen, into a shadow data
- * area.
- */
-static unsigned get_time_values_from_xen(void)
-{
-	struct vcpu_time_info   *src;
-	struct shadow_time_info *dst;
-
-	/* src is shared memory with the hypervisor, so we need to
-	   make sure we get a consistent snapshot, even in the face of
-	   being preempted. */
-	src = &__get_cpu_var(xen_vcpu)->time;
-	dst = &__get_cpu_var(shadow_time);
-
-	do {
-		dst->version = src->version;
-		rmb();		/* fetch version before data */
-		dst->tsc_timestamp     = src->tsc_timestamp;
-		dst->system_timestamp  = src->system_time;
-		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
-		dst->tsc_shift         = src->tsc_shift;
-		rmb();		/* test version after fetching data */
-	} while ((src->version & 1) | (dst->version ^ src->version));
-
-	return dst->version;
-}
-
-/*
- * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
- * yielding a 64-bit result.
- */
-static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
-{
-	u64 product;
-#ifdef __i386__
-	u32 tmp1, tmp2;
-#endif
-
-	if (shift < 0)
-		delta >>= -shift;
-	else
-		delta <<= shift;
-
-#ifdef __i386__
-	__asm__ (
-		"mul  %5       ; "
-		"mov  %4,%%eax ; "
-		"mov  %%edx,%4 ; "
-		"mul  %5       ; "
-		"xor  %5,%5    ; "
-		"add  %4,%%eax ; "
-		"adc  %5,%%edx ; "
-		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
-		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif __x86_64__
-	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
-#else
-#error implement me!
-#endif
-
-	return product;
-}
-
-static u64 get_nsec_offset(struct shadow_time_info *shadow)
-{
-	u64 now, delta;
-	now = native_read_tsc();
-	delta = now - shadow->tsc_timestamp;
-	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
-}
-
 static cycle_t xen_clocksource_read(void)
 {
-	struct shadow_time_info *shadow = &get_cpu_var(shadow_time);
+        struct pvclock_vcpu_time_info *src;
 	cycle_t ret;
-	unsigned version;
-
-	do {
-		version = get_time_values_from_xen();
-		barrier();
-		ret = shadow->system_timestamp + get_nsec_offset(shadow);
-		barrier();
-	} while (version != __get_cpu_var(xen_vcpu)->time.version);
-
-	put_cpu_var(shadow_time);
 
+	src = &get_cpu_var(xen_vcpu)->time;
+	ret = pvclock_clocksource_read(src);
+	put_cpu_var(xen_vcpu);
 	return ret;
 }
 
 static void xen_read_wallclock(struct timespec *ts)
 {
-	const struct shared_info *s = HYPERVISOR_shared_info;
+	struct shared_info *s = HYPERVISOR_shared_info;
-	u32 version;
+	struct pvclock_wall_clock *wall_clock = &(s->wc);
-	u64 delta;
+        struct pvclock_vcpu_time_info *vcpu_time;
-	struct timespec now;
 
-	/* get wallclock at system boot */
+	vcpu_time = &get_cpu_var(xen_vcpu)->time;
-	do {
+	pvclock_read_wallclock(wall_clock, vcpu_time, ts);
-		version = s->wc_version;
+	put_cpu_var(xen_vcpu);
-		rmb();		/* fetch version before time */
-		now.tv_sec  = s->wc_sec;
-		now.tv_nsec = s->wc_nsec;
-		rmb();		/* fetch time before checking version */
-	} while ((s->wc_version & 1) | (version ^ s->wc_version));
-
-	delta = xen_clocksource_read();	/* time since system boot */
-	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
-
-	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
-	now.tv_sec = delta;
-
-	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
 
 unsigned long xen_get_wallclock(void)
@@ -345,7 +240,6 @@ unsigned long xen_get_wallclock(void)
 	struct timespec ts;
 
 	xen_read_wallclock(&ts);
-
 	return ts.tv_sec;
 }
 
@@ -569,8 +463,6 @@ __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
 
-	get_time_values_from_xen();
-
 	clocksource_register(&xen_clocksource);
 
 	if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {

arch/x86/xen/xen-head.S

@@ -17,7 +17,7 @@ ENTRY(startup_xen)
 
 	__FINIT
 
-.pushsection .bss.page_aligned
+.pushsection .text
 	.align PAGE_SIZE_asm
 ENTRY(hypercall_page)
 	.skip 0x1000
@@ -30,11 +30,7 @@ ENTRY(hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          .long  startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long  hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .asciz "!writable_page_tables|pae_pgdir_above_4gb")
-#ifdef CONFIG_X86_PAE
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
-#else
-	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "no")
-#endif
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
 
 #endif /*CONFIG_XEN */

drivers/acpi/ac.c

@@ -233,6 +233,9 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 
 	device = ac->device;
 	switch (event) {
+	default:
+		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
+				  "Unsupported event [0x%x]\n", event));
 	case ACPI_AC_NOTIFY_STATUS:
 	case ACPI_NOTIFY_BUS_CHECK:
 	case ACPI_NOTIFY_DEVICE_CHECK:
@@ -244,11 +247,6 @@ static void acpi_ac_notify(acpi_handle handle, u32 event, void *data)
 #ifdef CONFIG_ACPI_SYSFS_POWER
 		kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
 #endif
-		break;
-	default:
-		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
-				  "Unsupported event [0x%x]\n", event));
-		break;
 	}
 
 	return;

drivers/acpi/video.c

@@ -1713,7 +1713,8 @@ acpi_video_bus_get_devices(struct acpi_video_bus *video,
 
 		status = acpi_video_bus_get_one_device(dev, video);
 		if (ACPI_FAILURE(status)) {
-			ACPI_EXCEPTION((AE_INFO, status, "Cant attach device"));
+			ACPI_DEBUG_PRINT((ACPI_DB_WARN,
+					"Cant attach device"));
 			continue;
 		}
 	}

drivers/ata/Kconfig

@@ -651,9 +651,17 @@ config PATA_WINBOND_VLB
 	  Support for the Winbond W83759A controller on Vesa Local Bus
 	  systems.
 
+config HAVE_PATA_PLATFORM
+	bool
+	help
+	  This is an internal configuration node for any machine that
+	  uses pata-platform driver to enable the relevant driver in the
+	  configuration structure without having to submit endless patches
+	  to update the PATA_PLATFORM entry.
+
 config PATA_PLATFORM
 	tristate "Generic platform device PATA support"
-	depends on EMBEDDED || ARCH_RPC || PPC
+	depends on EMBEDDED || ARCH_RPC || PPC || HAVE_PATA_PLATFORM
 	help
 	  This option enables support for generic directly connected ATA
 	  devices commonly found on embedded systems.

drivers/ata/ahci.c

@@ -90,6 +90,7 @@ enum {
 	board_ahci_mv		= 4,
 	board_ahci_sb700	= 5,
 	board_ahci_mcp65	= 6,
+	board_ahci_nopmp	= 7,
 
 	/* global controller registers */
 	HOST_CAP		= 0x00, /* host capabilities */
@@ -401,6 +402,14 @@ static const struct ata_port_info ahci_port_info[] = {
 		.udma_mask	= ATA_UDMA6,
 		.port_ops	= &ahci_ops,
 	},
+	/* board_ahci_nopmp */
+	{
+		AHCI_HFLAGS	(AHCI_HFLAG_NO_PMP),
+		.flags		= AHCI_FLAG_COMMON,
+		.pio_mask	= 0x1f, /* pio0-4 */
+		.udma_mask	= ATA_UDMA6,
+		.port_ops	= &ahci_ops,
+	},
 };
 
 static const struct pci_device_id ahci_pci_tbl[] = {
@@ -525,9 +534,9 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(NVIDIA, 0x0bc7), board_ahci },		/* MCP7B */
 
 	/* SiS */
-	{ PCI_VDEVICE(SI, 0x1184), board_ahci }, /* SiS 966 */
+	{ PCI_VDEVICE(SI, 0x1184), board_ahci_nopmp },		/* SiS 966 */
-	{ PCI_VDEVICE(SI, 0x1185), board_ahci }, /* SiS 966 */
+	{ PCI_VDEVICE(SI, 0x1185), board_ahci_nopmp },		/* SiS 968 */
-	{ PCI_VDEVICE(SI, 0x0186), board_ahci }, /* SiS 968 */
+	{ PCI_VDEVICE(SI, 0x0186), board_ahci_nopmp },		/* SiS 968 */
 
 	/* Marvell */
 	{ PCI_VDEVICE(MARVELL, 0x6145), board_ahci_mv },	/* 6145 */
@@ -653,6 +662,14 @@ static void ahci_save_initial_config(struct pci_dev *pdev,
 		cap &= ~HOST_CAP_PMP;
 	}
 
+	if (pdev->vendor == PCI_VENDOR_ID_JMICRON && pdev->device == 0x2361 &&
+	    port_map != 1) {
+		dev_printk(KERN_INFO, &pdev->dev,
+			   "JMB361 has only one port, port_map 0x%x -> 0x%x\n",
+			   port_map, 1);
+		port_map = 1;
+	}
+
 	/*
 	 * Temporary Marvell 6145 hack: PATA port presence
 	 * is asserted through the standard AHCI port

drivers/ata/ata_piix.c

@@ -1042,6 +1042,13 @@ static int piix_broken_suspend(void)
 				DMI_MATCH(DMI_PRODUCT_NAME, "Tecra M4"),
 			},
 		},
+		{
+			.ident = "TECRA M4",
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "TECRA M4"),
+			},
+		},
 		{
 			.ident = "TECRA M5",
 			.matches = {

drivers/ata/libata-core.c

@@ -4297,7 +4297,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc)
 }
 
 /**
- *	ata_check_atapi_dma - Check whether ATAPI DMA can be supported
+ *	atapi_check_dma - Check whether ATAPI DMA can be supported
  *	@qc: Metadata associated with taskfile to check
  *
  *	Allow low-level driver to filter ATA PACKET commands, returning
@@ -4310,7 +4310,7 @@ void ata_sg_clean(struct ata_queued_cmd *qc)
  *	RETURNS: 0 when ATAPI DMA can be used
  *               nonzero otherwise
  */
-int ata_check_atapi_dma(struct ata_queued_cmd *qc)
+int atapi_check_dma(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 

drivers/ata/libata-scsi.c

@@ -2343,8 +2343,8 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 {
 	struct scsi_cmnd *scmd = qc->scsicmd;
 	struct ata_device *dev = qc->dev;
-	int using_pio = (dev->flags & ATA_DFLAG_PIO);
 	int nodata = (scmd->sc_data_direction == DMA_NONE);
+	int using_pio = !nodata && (dev->flags & ATA_DFLAG_PIO);
 	unsigned int nbytes;
 
 	memset(qc->cdb, 0, dev->cdb_len);
@@ -2362,7 +2362,7 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 	ata_qc_set_pc_nbytes(qc);
 
 	/* check whether ATAPI DMA is safe */
-	if (!using_pio && ata_check_atapi_dma(qc))
+	if (!nodata && !using_pio && atapi_check_dma(qc))
 		using_pio = 1;
 
 	/* Some controller variants snoop this value for Packet
@@ -2402,13 +2402,11 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc)
 	qc->tf.lbam = (nbytes & 0xFF);
 	qc->tf.lbah = (nbytes >> 8);
 
-	if (using_pio || nodata) {
-		/* no data, or PIO data xfer */
 	if (nodata)
 		qc->tf.protocol = ATAPI_PROT_NODATA;
-		else
+	else if (using_pio)
 		qc->tf.protocol = ATAPI_PROT_PIO;
-	} else {
+	else {
 		/* DMA data xfer */
 		qc->tf.protocol = ATAPI_PROT_DMA;
 		qc->tf.feature |= ATAPI_PKT_DMA;

drivers/ata/libata.h

@@ -106,7 +106,7 @@ extern void ata_sg_clean(struct ata_queued_cmd *qc);
 extern void ata_qc_free(struct ata_queued_cmd *qc);
 extern void ata_qc_issue(struct ata_queued_cmd *qc);
 extern void __ata_qc_complete(struct ata_queued_cmd *qc);
-extern int ata_check_atapi_dma(struct ata_queued_cmd *qc);
+extern int atapi_check_dma(struct ata_queued_cmd *qc);
 extern void swap_buf_le16(u16 *buf, unsigned int buf_words);
 extern void ata_dev_init(struct ata_device *dev);
 extern void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp);

drivers/ata/pata_pcmcia.c

@@ -414,6 +414,7 @@ static struct pcmcia_device_id pcmcia_devices[] = {
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "PCIDE", 0x547e66dc, 0x5c5ab149),
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "PCIDEII", 0x547e66dc, 0xb3662674),
 	PCMCIA_DEVICE_PROD_ID12("LOOKMEET", "CBIDE2      ", 0xe37be2b5, 0x8671043b),
+	PCMCIA_DEVICE_PROD_ID12("M-Systems", "CF300", 0x7ed2ad87, 0x7e9e78ee),
 	PCMCIA_DEVICE_PROD_ID12("M-Systems", "CF500", 0x7ed2ad87, 0x7a13045c),
 	PCMCIA_DEVICE_PROD_ID2("NinjaATA-", 0xebe0bd79),
 	PCMCIA_DEVICE_PROD_ID12("PCMCIA", "CD-ROM", 0x281f1c5d, 0x66536591),
@@ -424,6 +425,7 @@ static struct pcmcia_device_id pcmcia_devices[] = {
 	PCMCIA_DEVICE_PROD_ID12("SMI VENDOR", "SMI PRODUCT", 0x30896c92, 0x703cc5f6),
 	PCMCIA_DEVICE_PROD_ID12("TOSHIBA", "MK2001MPL", 0xb4585a1a, 0x3489e003),
 	PCMCIA_DEVICE_PROD_ID1("TRANSCEND    512M   ", 0xd0909443),
+	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF45", 0x709b1bf1, 0xf68b6f32),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF80", 0x709b1bf1, 0x2a54d4b1),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS2GCF120", 0x709b1bf1, 0x969aa4f2),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF120", 0x709b1bf1, 0xf54a91c8),

drivers/ata/sata_mv.c

@@ -1322,6 +1322,9 @@ static int mv_port_start(struct ata_port *ap)
 		goto out_port_free_dma_mem;
 	memset(pp->crpb, 0, MV_CRPB_Q_SZ);
 
+	/* 6041/6081 Rev. "C0" (and newer) are okay with async notify */
+	if (hpriv->hp_flags & MV_HP_ERRATA_60X1C0)
+		ap->flags |= ATA_FLAG_AN;
 	/*
 	 * For GEN_I, there's no NCQ, so we only allocate a single sg_tbl.
 	 * For later hardware, we need one unique sg_tbl per NCQ tag.
@@ -1592,6 +1595,24 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc)
 
 	if ((qc->tf.protocol != ATA_PROT_DMA) &&
 	    (qc->tf.protocol != ATA_PROT_NCQ)) {
+		static int limit_warnings = 10;
+		/*
+		 * Errata SATA#16, SATA#24: warn if multiple DRQs expected.
+		 *
+		 * Someday, we might implement special polling workarounds
+		 * for these, but it all seems rather unnecessary since we
+		 * normally use only DMA for commands which transfer more
+		 * than a single block of data.
+		 *
+		 * Much of the time, this could just work regardless.
+		 * So for now, just log the incident, and allow the attempt.
+		 */
+		if (limit_warnings && (qc->nbytes / qc->sect_size) > 1) {
+			--limit_warnings;
+			ata_link_printk(qc->dev->link, KERN_WARNING, DRV_NAME
+					": attempting PIO w/multiple DRQ: "
+					"this may fail due to h/w errata\n");
+		}
 		/*
 		 * We're about to send a non-EDMA capable command to the
 		 * port.  Turn off EDMA so there won't be problems accessing

drivers/char/agp/intel-agp.c

@@ -948,7 +948,7 @@ static void intel_i9xx_setup_flush(void)
 	intel_private.ifp_resource.flags = IORESOURCE_MEM;
 
 	/* Setup chipset flush for 915 */
-	if (IS_I965 || IS_G33) {
+	if (IS_I965 || IS_G33 || IS_G4X) {
 		intel_i965_g33_setup_chipset_flush();
 	} else {
 		intel_i915_setup_chipset_flush();

drivers/char/drm/ati_pcigart.c

@@ -76,7 +76,7 @@ int drm_ati_pcigart_cleanup(struct drm_device *dev, struct drm_ati_pcigart_info
 		for (i = 0; i < pages; i++) {
 			if (!entry->busaddr[i])
 				break;
-			pci_unmap_single(dev->pdev, entry->busaddr[i],
+			pci_unmap_page(dev->pdev, entry->busaddr[i],
 					 PAGE_SIZE, PCI_DMA_TODEVICE);
 		}
 
@@ -137,10 +137,8 @@ int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *ga
 
 	for (i = 0; i < pages; i++) {
 		/* we need to support large memory configurations */
-		entry->busaddr[i] = pci_map_single(dev->pdev,
+		entry->busaddr[i] = pci_map_page(dev->pdev, entry->pagelist[i],
-						   page_address(entry->
+						 0, PAGE_SIZE, PCI_DMA_TODEVICE);
-								pagelist[i]),
-						   PAGE_SIZE, PCI_DMA_TODEVICE);
 		if (entry->busaddr[i] == 0) {
 			DRM_ERROR("unable to map PCIGART pages!\n");
 			drm_ati_pcigart_cleanup(dev, gart_info);

drivers/char/drm/drm.h

@@ -628,7 +628,7 @@ struct drm_set_version {
 #define DRM_IOCTL_AGP_BIND		DRM_IOW( 0x36, struct drm_agp_binding)
 #define DRM_IOCTL_AGP_UNBIND		DRM_IOW( 0x37, struct drm_agp_binding)
 
-#define DRM_IOCTL_SG_ALLOC		DRM_IOW( 0x38, struct drm_scatter_gather)
+#define DRM_IOCTL_SG_ALLOC		DRM_IOWR(0x38, struct drm_scatter_gather)
 #define DRM_IOCTL_SG_FREE		DRM_IOW( 0x39, struct drm_scatter_gather)
 
 #define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)

drivers/char/drm/drm_drv.c

@@ -470,17 +470,18 @@ int drm_ioctl(struct inode *inode, struct file *filp,
 	if ((nr >= DRM_COMMAND_BASE) && (nr < DRM_COMMAND_END) &&
 	    (nr < DRM_COMMAND_BASE + dev->driver->num_ioctls))
 		ioctl = &dev->driver->ioctls[nr - DRM_COMMAND_BASE];
-	else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE))
+	else if ((nr >= DRM_COMMAND_END) || (nr < DRM_COMMAND_BASE)) {
 		ioctl = &drm_ioctls[nr];
-	else
+		cmd = ioctl->cmd;
+	} else
 		goto err_i1;
 
+	/* Do not trust userspace, use our own definition */
 	func = ioctl->func;
 	/* is there a local override? */
 	if ((nr == DRM_IOCTL_NR(DRM_IOCTL_DMA)) && dev->driver->dma_ioctl)
 		func = dev->driver->dma_ioctl;
 
-
 	if (!func) {
 		DRM_DEBUG("no function\n");
 		retcode = -EINVAL;

drivers/char/drm/drm_pciids.h

@@ -103,20 +103,18 @@
 	{0x1002, 0x5653, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5834, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP}, \
 	{0x1002, 0x5835, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP|RADEON_IS_MOBILITY}, \
-	{0x1002, 0x5954, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5954, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5955, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5955, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5974, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5974, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5975, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5975, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
 	{0x1002, 0x5960, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5961, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5962, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5964, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5965, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5969, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV100}, \
-	{0x1002, 0x5a41, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a42, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
 	{0x1002, 0x5b60, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5b62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5b63, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
@@ -411,4 +409,7 @@
 	{0x8086, 0x2a02, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
 	{0x8086, 0x2a12, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
 	{0x8086, 0x2a42, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
+	{0x8086, 0x2e02, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
+	{0x8086, 0x2e12, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
+	{0x8086, 0x2e22, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, \
 	{0, 0, 0}

drivers/char/drm/i915_drv.c

@@ -389,6 +389,7 @@ static int i915_resume(struct drm_device *dev)
 	pci_restore_state(dev->pdev);
 	if (pci_enable_device(dev->pdev))
 		return -1;
+	pci_set_master(dev->pdev);
 
 	pci_write_config_byte(dev->pdev, LBB, dev_priv->saveLBB);
 

drivers/char/drm/i915_drv.h

@@ -1112,12 +1112,19 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller);
 		       (dev)->pci_device == 0x29A2 || \
 		       (dev)->pci_device == 0x2A02 || \
 		       (dev)->pci_device == 0x2A12 || \
-		       (dev)->pci_device == 0x2A42)
+		       (dev)->pci_device == 0x2A42 || \
+		       (dev)->pci_device == 0x2E02 || \
+		       (dev)->pci_device == 0x2E12 || \
+		       (dev)->pci_device == 0x2E22)
 
 #define IS_I965GM(dev) ((dev)->pci_device == 0x2A02)
 
 #define IS_IGD_GM(dev) ((dev)->pci_device == 0x2A42)
 
+#define IS_G4X(dev) ((dev)->pci_device == 0x2E02 || \
+		     (dev)->pci_device == 0x2E12 || \
+		     (dev)->pci_device == 0x2E22)
+
 #define IS_G33(dev)    ((dev)->pci_device == 0x29C2 ||	\
 			(dev)->pci_device == 0x29B2 ||	\
 			(dev)->pci_device == 0x29D2)
@@ -1128,7 +1135,7 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller);
 #define IS_MOBILE(dev) (IS_I830(dev) || IS_I85X(dev) || IS_I915GM(dev) || \
 			IS_I945GM(dev) || IS_I965GM(dev) || IS_IGD_GM(dev))
 
-#define I915_NEED_GFX_HWS(dev) (IS_G33(dev) || IS_IGD_GM(dev))
+#define I915_NEED_GFX_HWS(dev) (IS_G33(dev) || IS_IGD_GM(dev) || IS_G4X(dev))
 
 #define PRIMARY_RINGBUFFER_SIZE         (128*1024)
 

drivers/char/drm/r300_cmdbuf.c

@@ -189,18 +189,12 @@ void r300_init_reg_flags(struct drm_device *dev)
 	ADD_RANGE(R300_RE_CULL_CNTL, 1);
 	ADD_RANGE(0x42C0, 2);
 	ADD_RANGE(R300_RS_CNTL_0, 2);
-	ADD_RANGE(R300_RS_INTERP_0, 8);
+
-	ADD_RANGE(R300_RS_ROUTE_0, 8);
+	ADD_RANGE(R300_SC_HYPERZ, 2);
-	ADD_RANGE(0x43A4, 2);
 	ADD_RANGE(0x43E8, 1);
-	ADD_RANGE(R300_PFS_CNTL_0, 3);
+
-	ADD_RANGE(R300_PFS_NODE_0, 4);
-	ADD_RANGE(R300_PFS_TEXI_0, 64);
 	ADD_RANGE(0x46A4, 5);
-	ADD_RANGE(R300_PFS_INSTR0_0, 64);
+
-	ADD_RANGE(R300_PFS_INSTR1_0, 64);
-	ADD_RANGE(R300_PFS_INSTR2_0, 64);
-	ADD_RANGE(R300_PFS_INSTR3_0, 64);
 	ADD_RANGE(R300_RE_FOG_STATE, 1);
 	ADD_RANGE(R300_FOG_COLOR_R, 3);
 	ADD_RANGE(R300_PP_ALPHA_TEST, 2);
@@ -215,14 +209,12 @@ void r300_init_reg_flags(struct drm_device *dev)
 	ADD_RANGE(0x4E50, 9);
 	ADD_RANGE(0x4E88, 1);
 	ADD_RANGE(0x4EA0, 2);
-	ADD_RANGE(R300_RB3D_ZSTENCIL_CNTL_0, 3);
+	ADD_RANGE(R300_ZB_CNTL, 3);
-	ADD_RANGE(R300_RB3D_ZSTENCIL_FORMAT, 4);
+	ADD_RANGE(R300_ZB_FORMAT, 4);
-	ADD_RANGE_MARK(R300_RB3D_DEPTHOFFSET, 1, MARK_CHECK_OFFSET);	/* check offset */
+	ADD_RANGE_MARK(R300_ZB_DEPTHOFFSET, 1, MARK_CHECK_OFFSET);	/* check offset */
-	ADD_RANGE(R300_RB3D_DEPTHPITCH, 1);
+	ADD_RANGE(R300_ZB_DEPTHPITCH, 1);
-	ADD_RANGE(0x4F28, 1);
+	ADD_RANGE(R300_ZB_DEPTHCLEARVALUE, 1);
-	ADD_RANGE(0x4F30, 2);
+	ADD_RANGE(R300_ZB_ZMASK_OFFSET, 13);
-	ADD_RANGE(0x4F44, 1);
-	ADD_RANGE(0x4F54, 1);
 
 	ADD_RANGE(R300_TX_FILTER_0, 16);
 	ADD_RANGE(R300_TX_FILTER1_0, 16);
@@ -235,13 +227,32 @@ void r300_init_reg_flags(struct drm_device *dev)
 	ADD_RANGE(R300_TX_BORDER_COLOR_0, 16);
 
 	/* Sporadic registers used as primitives are emitted */
-	ADD_RANGE(R300_RB3D_ZCACHE_CTLSTAT, 1);
+	ADD_RANGE(R300_ZB_ZCACHE_CTLSTAT, 1);
 	ADD_RANGE(R300_RB3D_DSTCACHE_CTLSTAT, 1);
 	ADD_RANGE(R300_VAP_INPUT_ROUTE_0_0, 8);
 	ADD_RANGE(R300_VAP_INPUT_ROUTE_1_0, 8);
 
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RV515) {
-		ADD_RANGE(0x4074, 16);
+		ADD_RANGE(R500_VAP_INDEX_OFFSET, 1);
+		ADD_RANGE(R500_US_CONFIG, 2);
+		ADD_RANGE(R500_US_CODE_ADDR, 3);
+		ADD_RANGE(R500_US_FC_CTRL, 1);
+		ADD_RANGE(R500_RS_IP_0, 16);
+		ADD_RANGE(R500_RS_INST_0, 16);
+		ADD_RANGE(R500_RB3D_COLOR_CLEAR_VALUE_AR, 2);
+		ADD_RANGE(R500_RB3D_CONSTANT_COLOR_AR, 2);
+		ADD_RANGE(R500_ZB_FIFO_SIZE, 2);
+	} else {
+		ADD_RANGE(R300_PFS_CNTL_0, 3);
+		ADD_RANGE(R300_PFS_NODE_0, 4);
+		ADD_RANGE(R300_PFS_TEXI_0, 64);
+		ADD_RANGE(R300_PFS_INSTR0_0, 64);
+		ADD_RANGE(R300_PFS_INSTR1_0, 64);
+		ADD_RANGE(R300_PFS_INSTR2_0, 64);
+		ADD_RANGE(R300_PFS_INSTR3_0, 64);
+		ADD_RANGE(R300_RS_INTERP_0, 8);
+		ADD_RANGE(R300_RS_ROUTE_0, 8);
+
 	}
 }
 
@@ -707,8 +718,9 @@ static __inline__ void r300_pacify(drm_radeon_private_t *dev_priv)
 	BEGIN_RING(6);
 	OUT_RING(CP_PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));
 	OUT_RING(R300_RB3D_DSTCACHE_UNKNOWN_0A);
-	OUT_RING(CP_PACKET0(R300_RB3D_ZCACHE_CTLSTAT, 0));
+	OUT_RING(CP_PACKET0(R300_ZB_ZCACHE_CTLSTAT, 0));
-	OUT_RING(R300_RB3D_ZCACHE_UNKNOWN_03);
+	OUT_RING(R300_ZB_ZCACHE_CTLSTAT_ZC_FLUSH_FLUSH_AND_FREE|
+		 R300_ZB_ZCACHE_CTLSTAT_ZC_FREE_FREE);
 	OUT_RING(CP_PACKET3(RADEON_CP_NOP, 0));
 	OUT_RING(0x0);
 	ADVANCE_RING();
@@ -828,6 +840,54 @@ static int r300_scratch(drm_radeon_private_t *dev_priv,
 	return 0;
 }
 
+/**
+ * Uploads user-supplied vertex program instructions or parameters onto
+ * the graphics card.
+ * Called by r300_do_cp_cmdbuf.
+ */
+static inline int r300_emit_r500fp(drm_radeon_private_t *dev_priv,
+				       drm_radeon_kcmd_buffer_t *cmdbuf,
+				       drm_r300_cmd_header_t header)
+{
+	int sz;
+	int addr;
+	int type;
+	int clamp;
+	int stride;
+	RING_LOCALS;
+
+	sz = header.r500fp.count;
+	/* address is 9 bits 0 - 8, bit 1 of flags is part of address */
+	addr = ((header.r500fp.adrhi_flags & 1) << 8) | header.r500fp.adrlo;
+
+	type = !!(header.r500fp.adrhi_flags & R500FP_CONSTANT_TYPE);
+	clamp = !!(header.r500fp.adrhi_flags & R500FP_CONSTANT_CLAMP);
+
+	addr |= (type << 16);
+	addr |= (clamp << 17);
+
+	stride = type ? 4 : 6;
+
+	DRM_DEBUG("r500fp %d %d type: %d\n", sz, addr, type);
+	if (!sz)
+		return 0;
+	if (sz * stride * 4 > cmdbuf->bufsz)
+		return -EINVAL;
+
+	BEGIN_RING(3 + sz * stride);
+	OUT_RING_REG(R500_GA_US_VECTOR_INDEX, addr);
+	OUT_RING(CP_PACKET0_TABLE(R500_GA_US_VECTOR_DATA, sz * stride - 1));
+	OUT_RING_TABLE((int *)cmdbuf->buf, sz * stride);
+
+	ADVANCE_RING();
+
+	cmdbuf->buf += sz * stride * 4;
+	cmdbuf->bufsz -= sz * stride * 4;
+
+	return 0;
+}
+
+
 /**
  * Parses and validates a user-supplied command buffer and emits appropriate
  * commands on the DMA ring buffer.
@@ -963,6 +1023,19 @@ int r300_do_cp_cmdbuf(struct drm_device *dev,
 			}
 			break;
 
+		case R300_CMD_R500FP:
+			if ((dev_priv->flags & RADEON_FAMILY_MASK) < CHIP_RV515) {
+				DRM_ERROR("Calling r500 command on r300 card\n");
+				ret = -EINVAL;
+				goto cleanup;
+			}
+			DRM_DEBUG("R300_CMD_R500FP\n");
+			ret = r300_emit_r500fp(dev_priv, cmdbuf, header);
+			if (ret) {
+				DRM_ERROR("r300_emit_r500fp failed\n");
+				goto cleanup;
+			}
+			break;
 		default:
 			DRM_ERROR("bad cmd_type %i at %p\n",
 				  header.header.cmd_type,

drivers/char/drm/r300_reg.h

@@ -702,6 +702,27 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 #		define R300_RS_ROUTE_1_UNKNOWN11         (1 << 11)
 /* END: Rasterization / Interpolators - many guesses */
 
+/* Hierarchical Z Enable */
+#define R300_SC_HYPERZ                   0x43a4
+#	define R300_SC_HYPERZ_DISABLE     (0 << 0)
+#	define R300_SC_HYPERZ_ENABLE      (1 << 0)
+#	define R300_SC_HYPERZ_MIN         (0 << 1)
+#	define R300_SC_HYPERZ_MAX         (1 << 1)
+#	define R300_SC_HYPERZ_ADJ_256     (0 << 2)
+#	define R300_SC_HYPERZ_ADJ_128     (1 << 2)
+#	define R300_SC_HYPERZ_ADJ_64      (2 << 2)
+#	define R300_SC_HYPERZ_ADJ_32      (3 << 2)
+#	define R300_SC_HYPERZ_ADJ_16      (4 << 2)
+#	define R300_SC_HYPERZ_ADJ_8       (5 << 2)
+#	define R300_SC_HYPERZ_ADJ_4       (6 << 2)
+#	define R300_SC_HYPERZ_ADJ_2       (7 << 2)
+#	define R300_SC_HYPERZ_HZ_Z0MIN_NO (0 << 5)
+#	define R300_SC_HYPERZ_HZ_Z0MIN    (1 << 5)
+#	define R300_SC_HYPERZ_HZ_Z0MAX_NO (0 << 6)
+#	define R300_SC_HYPERZ_HZ_Z0MAX    (1 << 6)
+
+#define R300_SC_EDGERULE                 0x43a8
+
 /* BEGIN: Scissors and cliprects */
 
 /* There are four clipping rectangles. Their corner coordinates are inclusive.
@@ -1346,7 +1367,7 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 /* Guess by Vladimir.
  * Set to 0A before 3D operations, set to 02 afterwards.
  */
-#define R300_RB3D_DSTCACHE_CTLSTAT          0x4E4C
+/*#define R300_RB3D_DSTCACHE_CTLSTAT          0x4E4C*/
 #       define R300_RB3D_DSTCACHE_UNKNOWN_02             0x00000002
 #       define R300_RB3D_DSTCACHE_UNKNOWN_0A             0x0000000A
 
@@ -1355,19 +1376,14 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
  * for this.
  * Bit (1<<8) is the "test" bit. so plain write is 6  - vd
  */
-#define R300_RB3D_ZSTENCIL_CNTL_0                   0x4F00
+#define R300_ZB_CNTL                             0x4F00
-#       define R300_RB3D_Z_DISABLED_1            0x00000010
+#	define R300_STENCIL_ENABLE		 (1 << 0)
-#       define R300_RB3D_Z_DISABLED_2            0x00000014
+#	define R300_Z_ENABLE		         (1 << 1)
-#       define R300_RB3D_Z_TEST                  0x00000012
+#	define R300_Z_WRITE_ENABLE		 (1 << 2)
-#       define R300_RB3D_Z_TEST_AND_WRITE        0x00000016
+#	define R300_Z_SIGNED_COMPARE		 (1 << 3)
-#       define R300_RB3D_Z_WRITE_ONLY		 0x00000006
+#	define R300_STENCIL_FRONT_BACK		 (1 << 4)
 
-#       define R300_RB3D_Z_TEST                  0x00000012
+#define R300_ZB_ZSTENCILCNTL                   0x4f04
-#       define R300_RB3D_Z_TEST_AND_WRITE        0x00000016
-#       define R300_RB3D_Z_WRITE_ONLY		 0x00000006
-#	define R300_RB3D_STENCIL_ENABLE		 0x00000001
-
-#define R300_RB3D_ZSTENCIL_CNTL_1                   0x4F04
 	/* functions */
 #	define R300_ZS_NEVER			0
 #	define R300_ZS_LESS			1
@@ -1387,52 +1403,166 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 #	define R300_ZS_INVERT			5
 #	define R300_ZS_INCR_WRAP		6
 #	define R300_ZS_DECR_WRAP		7
+#	define R300_Z_FUNC_SHIFT		0
 	/* front and back refer to operations done for front
 	   and back faces, i.e. separate stencil function support */
-#	define R300_RB3D_ZS1_DEPTH_FUNC_SHIFT		0
+#	define R300_S_FRONT_FUNC_SHIFT	        3
-#	define R300_RB3D_ZS1_FRONT_FUNC_SHIFT		3
+#	define R300_S_FRONT_SFAIL_OP_SHIFT	6
-#	define R300_RB3D_ZS1_FRONT_FAIL_OP_SHIFT	6
+#	define R300_S_FRONT_ZPASS_OP_SHIFT	9
-#	define R300_RB3D_ZS1_FRONT_ZPASS_OP_SHIFT	9
+#	define R300_S_FRONT_ZFAIL_OP_SHIFT      12
-#	define R300_RB3D_ZS1_FRONT_ZFAIL_OP_SHIFT      12
+#	define R300_S_BACK_FUNC_SHIFT           15
-#	define R300_RB3D_ZS1_BACK_FUNC_SHIFT           15
+#	define R300_S_BACK_SFAIL_OP_SHIFT       18
-#	define R300_RB3D_ZS1_BACK_FAIL_OP_SHIFT        18
+#	define R300_S_BACK_ZPASS_OP_SHIFT       21
-#	define R300_RB3D_ZS1_BACK_ZPASS_OP_SHIFT       21
+#	define R300_S_BACK_ZFAIL_OP_SHIFT       24
-#	define R300_RB3D_ZS1_BACK_ZFAIL_OP_SHIFT       24
 
-#define R300_RB3D_ZSTENCIL_CNTL_2                   0x4F08
+#define R300_ZB_STENCILREFMASK                        0x4f08
-#	define R300_RB3D_ZS2_STENCIL_REF_SHIFT		0
+#	define R300_STENCILREF_SHIFT       0
-#	define R300_RB3D_ZS2_STENCIL_MASK		0xFF
+#	define R300_STENCILREF_MASK        0x000000ff
-#	define R300_RB3D_ZS2_STENCIL_MASK_SHIFT	        8
+#	define R300_STENCILMASK_SHIFT      8
-#	define R300_RB3D_ZS2_STENCIL_WRITE_MASK_SHIFT	16
+#	define R300_STENCILMASK_MASK       0x0000ff00
+#	define R300_STENCILWRITEMASK_SHIFT 16
+#	define R300_STENCILWRITEMASK_MASK  0x00ff0000
 
 /* gap */
 
-#define R300_RB3D_ZSTENCIL_FORMAT                   0x4F10
+#define R300_ZB_FORMAT                             0x4f10
-#	define R300_DEPTH_FORMAT_16BIT_INT_Z     (0 << 0)
+#	define R300_DEPTHFORMAT_16BIT_INT_Z   (0 << 0)
-#	define R300_DEPTH_FORMAT_24BIT_INT_Z     (2 << 0)
+#	define R300_DEPTHFORMAT_16BIT_13E3    (1 << 0)
-	/* 16 bit format or some aditional bit ? */
+#	define R300_DEPTHFORMAT_24BIT_INT_Z_8BIT_STENCIL   (2 << 0)
-#	define R300_DEPTH_FORMAT_UNK32          (32 << 0)
+/* reserved up to (15 << 0) */
+#	define R300_INVERT_13E3_LEADING_ONES  (0 << 4)
+#	define R300_INVERT_13E3_LEADING_ZEROS (1 << 4)
 
-#define R300_RB3D_EARLY_Z                           0x4F14
+#define R300_ZB_ZTOP                             0x4F14
-#	define R300_EARLY_Z_DISABLE              (0 << 0)
+#	define R300_ZTOP_DISABLE                 (0 << 0)
-#	define R300_EARLY_Z_ENABLE               (1 << 0)
+#	define R300_ZTOP_ENABLE                  (1 << 0)
 
 /* gap */
 
-#define R300_RB3D_ZCACHE_CTLSTAT            0x4F18 /* GUESS */
+#define R300_ZB_ZCACHE_CTLSTAT            0x4f18
-#       define R300_RB3D_ZCACHE_UNKNOWN_01  0x1
+#       define R300_ZB_ZCACHE_CTLSTAT_ZC_FLUSH_NO_EFFECT      (0 << 0)
-#       define R300_RB3D_ZCACHE_UNKNOWN_03  0x3
+#       define R300_ZB_ZCACHE_CTLSTAT_ZC_FLUSH_FLUSH_AND_FREE (1 << 0)
+#       define R300_ZB_ZCACHE_CTLSTAT_ZC_FREE_NO_EFFECT       (0 << 1)
+#       define R300_ZB_ZCACHE_CTLSTAT_ZC_FREE_FREE            (1 << 1)
+#       define R300_ZB_ZCACHE_CTLSTAT_ZC_BUSY_IDLE            (0 << 31)
+#       define R300_ZB_ZCACHE_CTLSTAT_ZC_BUSY_BUSY            (1 << 31)
+
+#define R300_ZB_BW_CNTL                     0x4f1c
+#	define R300_HIZ_DISABLE                              (0 << 0)
+#	define R300_HIZ_ENABLE                               (1 << 0)
+#	define R300_HIZ_MIN                                  (0 << 1)
+#	define R300_HIZ_MAX                                  (1 << 1)
+#	define R300_FAST_FILL_DISABLE                        (0 << 2)
+#	define R300_FAST_FILL_ENABLE                         (1 << 2)
+#	define R300_RD_COMP_DISABLE                          (0 << 3)
+#	define R300_RD_COMP_ENABLE                           (1 << 3)
+#	define R300_WR_COMP_DISABLE                          (0 << 4)
+#	define R300_WR_COMP_ENABLE                           (1 << 4)
+#	define R300_ZB_CB_CLEAR_RMW                          (0 << 5)
+#	define R300_ZB_CB_CLEAR_CACHE_LINEAR                 (1 << 5)
+#	define R300_FORCE_COMPRESSED_STENCIL_VALUE_DISABLE   (0 << 6)
+#	define R300_FORCE_COMPRESSED_STENCIL_VALUE_ENABLE    (1 << 6)
+
+#	define R500_ZEQUAL_OPTIMIZE_ENABLE                   (0 << 7)
+#	define R500_ZEQUAL_OPTIMIZE_DISABLE                  (1 << 7)
+#	define R500_SEQUAL_OPTIMIZE_ENABLE                   (0 << 8)
+#	define R500_SEQUAL_OPTIMIZE_DISABLE                  (1 << 8)
+
+#	define R500_BMASK_ENABLE                             (0 << 10)
+#	define R500_BMASK_DISABLE                            (1 << 10)
+#	define R500_HIZ_EQUAL_REJECT_DISABLE                 (0 << 11)
+#	define R500_HIZ_EQUAL_REJECT_ENABLE                  (1 << 11)
+#	define R500_HIZ_FP_EXP_BITS_DISABLE                  (0 << 12)
+#	define R500_HIZ_FP_EXP_BITS_1                        (1 << 12)
+#	define R500_HIZ_FP_EXP_BITS_2                        (2 << 12)
+#	define R500_HIZ_FP_EXP_BITS_3                        (3 << 12)
+#	define R500_HIZ_FP_EXP_BITS_4                        (4 << 12)
+#	define R500_HIZ_FP_EXP_BITS_5                        (5 << 12)
+#	define R500_HIZ_FP_INVERT_LEADING_ONES               (0 << 15)
+#	define R500_HIZ_FP_INVERT_LEADING_ZEROS              (1 << 15)
+#	define R500_TILE_OVERWRITE_RECOMPRESSION_ENABLE      (0 << 16)
+#	define R500_TILE_OVERWRITE_RECOMPRESSION_DISABLE     (1 << 16)
+#	define R500_CONTIGUOUS_6XAA_SAMPLES_ENABLE           (0 << 17)
+#	define R500_CONTIGUOUS_6XAA_SAMPLES_DISABLE          (1 << 17)
+#	define R500_PEQ_PACKING_DISABLE                      (0 << 18)
+#	define R500_PEQ_PACKING_ENABLE                       (1 << 18)
+#	define R500_COVERED_PTR_MASKING_DISABLE              (0 << 18)
+#	define R500_COVERED_PTR_MASKING_ENABLE               (1 << 18)
+
 
 /* gap */
 
-#define R300_RB3D_DEPTHOFFSET               0x4F20
+/* Z Buffer Address Offset.
-#define R300_RB3D_DEPTHPITCH                0x4F24
+ * Bits 31 to 5 are used for aligned Z buffer address offset for macro tiles.
-#       define R300_DEPTHPITCH_MASK              0x00001FF8 /* GUESS */
+ */
-#       define R300_DEPTH_TILE_ENABLE            (1 << 16) /* GUESS */
+#define R300_ZB_DEPTHOFFSET               0x4f20
-#       define R300_DEPTH_MICROTILE_ENABLE       (1 << 17) /* GUESS */
+
-#       define R300_DEPTH_ENDIAN_NO_SWAP         (0 << 18) /* GUESS */
+/* Z Buffer Pitch and Endian Control */
-#       define R300_DEPTH_ENDIAN_WORD_SWAP       (1 << 18) /* GUESS */
+#define R300_ZB_DEPTHPITCH                0x4f24
-#       define R300_DEPTH_ENDIAN_DWORD_SWAP      (2 << 18) /* GUESS */
+#       define R300_DEPTHPITCH_MASK              0x00003FFC
+#       define R300_DEPTHMACROTILE_DISABLE      (0 << 16)
+#       define R300_DEPTHMACROTILE_ENABLE       (1 << 16)
+#       define R300_DEPTHMICROTILE_LINEAR       (0 << 17)
+#       define R300_DEPTHMICROTILE_TILED        (1 << 17)
+#       define R300_DEPTHMICROTILE_TILED_SQUARE (2 << 17)
+#       define R300_DEPTHENDIAN_NO_SWAP         (0 << 18)
+#       define R300_DEPTHENDIAN_WORD_SWAP       (1 << 18)
+#       define R300_DEPTHENDIAN_DWORD_SWAP      (2 << 18)
+#       define R300_DEPTHENDIAN_HALF_DWORD_SWAP (3 << 18)
+
+/* Z Buffer Clear Value */
+#define R300_ZB_DEPTHCLEARVALUE                  0x4f28
+
+#define R300_ZB_ZMASK_OFFSET			 0x4f30
+#define R300_ZB_ZMASK_PITCH			 0x4f34
+#define R300_ZB_ZMASK_WRINDEX			 0x4f38
+#define R300_ZB_ZMASK_DWORD			 0x4f3c
+#define R300_ZB_ZMASK_RDINDEX			 0x4f40
+
+/* Hierarchical Z Memory Offset */
+#define R300_ZB_HIZ_OFFSET                       0x4f44
+
+/* Hierarchical Z Write Index */
+#define R300_ZB_HIZ_WRINDEX                      0x4f48
+
+/* Hierarchical Z Data */
+#define R300_ZB_HIZ_DWORD                        0x4f4c
+
+/* Hierarchical Z Read Index */
+#define R300_ZB_HIZ_RDINDEX                      0x4f50
+
+/* Hierarchical Z Pitch */
+#define R300_ZB_HIZ_PITCH                        0x4f54
+
+/* Z Buffer Z Pass Counter Data */
+#define R300_ZB_ZPASS_DATA                       0x4f58
+
+/* Z Buffer Z Pass Counter Address */
+#define R300_ZB_ZPASS_ADDR                       0x4f5c
+
+/* Depth buffer X and Y coordinate offset */
+#define R300_ZB_DEPTHXY_OFFSET                   0x4f60
+#	define R300_DEPTHX_OFFSET_SHIFT  1
+#	define R300_DEPTHX_OFFSET_MASK   0x000007FE
+#	define R300_DEPTHY_OFFSET_SHIFT  17
+#	define R300_DEPTHY_OFFSET_MASK   0x07FE0000
+
+/* Sets the fifo sizes */
+#define R500_ZB_FIFO_SIZE                        0x4fd0
+#	define R500_OP_FIFO_SIZE_FULL   (0 << 0)
+#	define R500_OP_FIFO_SIZE_HALF   (1 << 0)
+#	define R500_OP_FIFO_SIZE_QUATER (2 << 0)
+#	define R500_OP_FIFO_SIZE_EIGTHS (4 << 0)
+
+/* Stencil Reference Value and Mask for backfacing quads */
+/* R300_ZB_STENCILREFMASK handles front face */
+#define R500_ZB_STENCILREFMASK_BF                0x4fd4
+#	define R500_STENCILREF_SHIFT       0
+#	define R500_STENCILREF_MASK        0x000000ff
+#	define R500_STENCILMASK_SHIFT      8
+#	define R500_STENCILMASK_MASK       0x0000ff00
+#	define R500_STENCILWRITEMASK_SHIFT 16
+#	define R500_STENCILWRITEMASK_MASK  0x00ff0000
 
 /* BEGIN: Vertex program instruction set */
 
@@ -1623,4 +1753,20 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
  */
 #define R300_CP_CMD_BITBLT_MULTI	0xC0009B00
 
+#define R500_VAP_INDEX_OFFSET		0x208c
+
+#define R500_GA_US_VECTOR_INDEX         0x4250
+#define R500_GA_US_VECTOR_DATA          0x4254
+
+#define R500_RS_IP_0                    0x4074
+#define R500_RS_INST_0                  0x4320
+
+#define R500_US_CONFIG                  0x4600
+
+#define R500_US_FC_CTRL			0x4624
+#define R500_US_CODE_ADDR		0x4630
+
+#define R500_RB3D_COLOR_CLEAR_VALUE_AR  0x46c0
+#define R500_RB3D_CONSTANT_COLOR_AR     0x4ef8
+
 #endif /* _R300_REG_H */

drivers/char/drm/radeon_drm.h

@@ -240,6 +240,7 @@ typedef union {
 #	define R300_NEW_WAIT_2D_2D_CLEAN_3D_3D_CLEAN	0x8
 
 #define R300_CMD_SCRATCH		8
+#define R300_CMD_R500FP                 9
 
 typedef union {
 	unsigned int u;
@@ -268,6 +269,9 @@ typedef union {
 	struct {
 		unsigned char cmd_type, reg, n_bufs, flags;
 	} scratch;
+	struct {
+		unsigned char cmd_type, count, adrlo, adrhi_flags;
+	} r500fp;
 } drm_r300_cmd_header_t;
 
 #define RADEON_FRONT			0x1
@@ -278,6 +282,9 @@ typedef union {
 #define RADEON_USE_HIERZ		0x40000000
 #define RADEON_USE_COMP_ZBUF		0x20000000
 
+#define R500FP_CONSTANT_TYPE  (1 << 1)
+#define R500FP_CONSTANT_CLAMP (1 << 2)
+
 /* Primitive types
  */
 #define RADEON_POINTS			0x1
@@ -669,6 +676,7 @@ typedef struct drm_radeon_indirect {
 #define RADEON_PARAM_CARD_TYPE             12
 #define RADEON_PARAM_VBLANK_CRTC           13   /* VBLANK CRTC */
 #define RADEON_PARAM_FB_LOCATION           14   /* FB location */
+#define RADEON_PARAM_NUM_GB_PIPES          15   /* num GB pipes */
 
 typedef struct drm_radeon_getparam {
 	int param;

drivers/char/drm/radeon_drv.h

@@ -38,7 +38,7 @@
 
 #define DRIVER_NAME		"radeon"
 #define DRIVER_DESC		"ATI Radeon"
-#define DRIVER_DATE		"20060524"
+#define DRIVER_DATE		"20080528"
 
 /* Interface history:
  *
@@ -98,9 +98,10 @@
  * 1.26- Add support for variable size PCI(E) gart aperture
  * 1.27- Add support for IGP GART
  * 1.28- Add support for VBL on CRTC2
+ * 1.29- R500 3D cmd buffer support
  */
 #define DRIVER_MAJOR		1
-#define DRIVER_MINOR		28
+#define DRIVER_MINOR		29
 #define DRIVER_PATCHLEVEL	0
 
 /*
@@ -122,7 +123,7 @@ enum radeon_family {
 	CHIP_RV380,
 	CHIP_R420,
 	CHIP_RV410,
-	CHIP_RS400,
+	CHIP_RS480,
 	CHIP_RS690,
 	CHIP_RV515,
 	CHIP_R520,
@@ -294,6 +295,7 @@ typedef struct drm_radeon_private {
 	int vblank_crtc;
 	uint32_t irq_enable_reg;
 	int irq_enabled;
+	uint32_t r500_disp_irq_reg;
 
 	struct radeon_surface surfaces[RADEON_MAX_SURFACES];
 	struct radeon_virt_surface virt_surfaces[2 * RADEON_MAX_SURFACES];
@@ -307,6 +309,8 @@ typedef struct drm_radeon_private {
 	/* starting from here on, data is preserved accross an open */
 	uint32_t flags;		/* see radeon_chip_flags */
 	unsigned long fb_aper_offset;
+
+	int num_gb_pipes;
 } drm_radeon_private_t;
 
 typedef struct drm_radeon_buf_priv {
@@ -382,6 +386,7 @@ extern irqreturn_t radeon_driver_irq_handler(DRM_IRQ_ARGS);
 extern void radeon_driver_irq_preinstall(struct drm_device * dev);
 extern void radeon_driver_irq_postinstall(struct drm_device * dev);
 extern void radeon_driver_irq_uninstall(struct drm_device * dev);
+extern void radeon_enable_interrupt(struct drm_device *dev);
 extern int radeon_vblank_crtc_get(struct drm_device *dev);
 extern int radeon_vblank_crtc_set(struct drm_device *dev, int64_t value);
 
@@ -444,13 +449,13 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #define RADEON_PCIE_DATA                0x0034
 #define RADEON_PCIE_TX_GART_CNTL	0x10
 #	define RADEON_PCIE_TX_GART_EN		(1 << 0)
-#	define RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_PASS_THRU (0<<1)
+#	define RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_PASS_THRU (0 << 1)
-#	define RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_CLAMP_LO  (1<<1)
+#	define RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_CLAMP_LO  (1 << 1)
-#	define RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_DISCARD   (3<<1)
+#	define RADEON_PCIE_TX_GART_UNMAPPED_ACCESS_DISCARD   (3 << 1)
-#	define RADEON_PCIE_TX_GART_MODE_32_128_CACHE	(0<<3)
+#	define RADEON_PCIE_TX_GART_MODE_32_128_CACHE	(0 << 3)
-#	define RADEON_PCIE_TX_GART_MODE_8_4_128_CACHE	(1<<3)
+#	define RADEON_PCIE_TX_GART_MODE_8_4_128_CACHE	(1 << 3)
-#	define RADEON_PCIE_TX_GART_CHK_RW_VALID_EN      (1<<5)
+#	define RADEON_PCIE_TX_GART_CHK_RW_VALID_EN      (1 << 5)
-#	define RADEON_PCIE_TX_GART_INVALIDATE_TLB	(1<<8)
+#	define RADEON_PCIE_TX_GART_INVALIDATE_TLB	(1 << 8)
 #define RADEON_PCIE_TX_DISCARD_RD_ADDR_LO 0x11
 #define RADEON_PCIE_TX_DISCARD_RD_ADDR_HI 0x12
 #define RADEON_PCIE_TX_GART_BASE	0x13
@@ -459,14 +464,9 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #define RADEON_PCIE_TX_GART_END_LO	0x16
 #define RADEON_PCIE_TX_GART_END_HI	0x17
 
-#define RADEON_IGPGART_INDEX            0x168
+#define RS480_NB_MC_INDEX               0x168
-#define RADEON_IGPGART_DATA             0x16c
+#	define RS480_NB_MC_IND_WR_EN	(1 << 8)
-#define RADEON_IGPGART_UNK_18           0x18
+#define RS480_NB_MC_DATA                0x16c
-#define RADEON_IGPGART_CTRL             0x2b
-#define RADEON_IGPGART_BASE_ADDR        0x2c
-#define RADEON_IGPGART_FLUSH            0x2e
-#define RADEON_IGPGART_ENABLE           0x38
-#define RADEON_IGPGART_UNK_39           0x39
 
 #define RS690_MC_INDEX                  0x78
 #   define RS690_MC_INDEX_MASK          0x1ff
@@ -474,45 +474,91 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #   define RS690_MC_INDEX_WR_ACK        0x7f
 #define RS690_MC_DATA                   0x7c
 
-#define RS690_MC_MISC_CNTL              0x18
+/* MC indirect registers */
-#define RS690_MC_GART_FEATURE_ID        0x2b
+#define RS480_MC_MISC_CNTL              0x18
-#define RS690_MC_GART_BASE              0x2c
+#	define RS480_DISABLE_GTW	(1 << 1)
-#define RS690_MC_GART_CACHE_CNTL	0x2e
+/* switch between MCIND GART and MM GART registers. 0 = mmgart, 1 = mcind gart */
-#   define RS690_MC_GART_CC_NO_CHANGE   0x0
+#	define RS480_GART_INDEX_REG_EN	(1 << 12)
-#   define RS690_MC_GART_CC_CLEAR       0x1
+#	define RS690_BLOCK_GFX_D3_EN	(1 << 14)
-#   define RS690_MC_GART_CLEAR_STATUS   (1 << 1)
+#define RS480_K8_FB_LOCATION            0x1e
-#       define RS690_MC_GART_CLEAR_DONE     (0 << 1)
+#define RS480_GART_FEATURE_ID           0x2b
-#       define RS690_MC_GART_CLEAR_PENDING  (1 << 1)
+#	define RS480_HANG_EN	        (1 << 11)
-#define RS690_MC_AGP_SIZE               0x38
+#	define RS480_TLB_ENABLE	        (1 << 18)
-#   define RS690_MC_GART_DIS            0x0
+#	define RS480_P2P_ENABLE	        (1 << 19)
-#   define RS690_MC_GART_EN             0x1
+#	define RS480_GTW_LAC_EN	        (1 << 25)
-#   define RS690_MC_AGP_SIZE_32MB       (0 << 1)
+#	define RS480_2LEVEL_GART	(0 << 30)
-#   define RS690_MC_AGP_SIZE_64MB       (1 << 1)
+#	define RS480_1LEVEL_GART	(1 << 30)
-#   define RS690_MC_AGP_SIZE_128MB      (2 << 1)
+#	define RS480_PDC_EN	        (1 << 31)
-#   define RS690_MC_AGP_SIZE_256MB      (3 << 1)
+#define RS480_GART_BASE                 0x2c
-#   define RS690_MC_AGP_SIZE_512MB      (4 << 1)
+#define RS480_GART_CACHE_CNTRL          0x2e
-#   define RS690_MC_AGP_SIZE_1GB        (5 << 1)
+#	define RS480_GART_CACHE_INVALIDATE (1 << 0) /* wait for it to clear */
-#   define RS690_MC_AGP_SIZE_2GB        (6 << 1)
+#define RS480_AGP_ADDRESS_SPACE_SIZE    0x38
-#define RS690_MC_AGP_MODE_CONTROL       0x39
+#	define RS480_GART_EN	        (1 << 0)
+#	define RS480_VA_SIZE_32MB	(0 << 1)
+#	define RS480_VA_SIZE_64MB	(1 << 1)
+#	define RS480_VA_SIZE_128MB	(2 << 1)
+#	define RS480_VA_SIZE_256MB	(3 << 1)
+#	define RS480_VA_SIZE_512MB	(4 << 1)
+#	define RS480_VA_SIZE_1GB	(5 << 1)
+#	define RS480_VA_SIZE_2GB	(6 << 1)
+#define RS480_AGP_MODE_CNTL             0x39
+#	define RS480_POST_GART_Q_SIZE	(1 << 18)
+#	define RS480_NONGART_SNOOP	(1 << 19)
+#	define RS480_AGP_RD_BUF_SIZE	(1 << 20)
+#	define RS480_REQ_TYPE_SNOOP_SHIFT 22
+#	define RS480_REQ_TYPE_SNOOP_MASK  0x3
+#	define RS480_REQ_TYPE_SNOOP_DIS	(1 << 24)
+#define RS480_MC_MISC_UMA_CNTL          0x5f
+#define RS480_MC_MCLK_CNTL              0x7a
+#define RS480_MC_UMA_DUALCH_CNTL        0x86
+
 #define RS690_MC_FB_LOCATION            0x100
 #define RS690_MC_AGP_LOCATION           0x101
 #define RS690_MC_AGP_BASE               0x102
+#define RS690_MC_AGP_BASE_2             0x103
 
 #define R520_MC_IND_INDEX 0x70
-#define R520_MC_IND_WR_EN (1<<24)
+#define R520_MC_IND_WR_EN (1 << 24)
 #define R520_MC_IND_DATA  0x74
 
 #define RV515_MC_FB_LOCATION 0x01
 #define RV515_MC_AGP_LOCATION 0x02
+#define RV515_MC_AGP_BASE     0x03
+#define RV515_MC_AGP_BASE_2   0x04
 
 #define R520_MC_FB_LOCATION 0x04
 #define R520_MC_AGP_LOCATION 0x05
+#define R520_MC_AGP_BASE     0x06
+#define R520_MC_AGP_BASE_2   0x07
 
 #define RADEON_MPP_TB_CONFIG		0x01c0
 #define RADEON_MEM_CNTL			0x0140
 #define RADEON_MEM_SDRAM_MODE_REG	0x0158
+#define RADEON_AGP_BASE_2		0x015c /* r200+ only */
+#define RS480_AGP_BASE_2		0x0164
 #define RADEON_AGP_BASE			0x0170
 
+/* pipe config regs */
+#define R400_GB_PIPE_SELECT             0x402c
+#define R500_DYN_SCLK_PWMEM_PIPE        0x000d /* PLL */
+#define R500_SU_REG_DEST                0x42c8
+#define R300_GB_TILE_CONFIG             0x4018
+#       define R300_ENABLE_TILING       (1 << 0)
+#       define R300_PIPE_COUNT_RV350    (0 << 1)
+#       define R300_PIPE_COUNT_R300     (3 << 1)
+#       define R300_PIPE_COUNT_R420_3P  (6 << 1)
+#       define R300_PIPE_COUNT_R420     (7 << 1)
+#       define R300_TILE_SIZE_8         (0 << 4)
+#       define R300_TILE_SIZE_16        (1 << 4)
+#       define R300_TILE_SIZE_32        (2 << 4)
+#       define R300_SUBPIXEL_1_12       (0 << 16)
+#       define R300_SUBPIXEL_1_16       (1 << 16)
+#define R300_DST_PIPE_CONFIG            0x170c
+#       define R300_PIPE_AUTO_CONFIG    (1 << 31)
+#define R300_RB2D_DSTCACHE_MODE         0x3428
+#       define R300_DC_AUTOFLUSH_ENABLE (1 << 8)
+#       define R300_DC_DC_DISABLE_IGNORE_PE (1 << 17)
+
 #define RADEON_RB3D_COLOROFFSET		0x1c40
 #define RADEON_RB3D_COLORPITCH		0x1c48
 
@@ -616,11 +662,12 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #define RADEON_PP_TXFILTER_1		0x1c6c
 #define RADEON_PP_TXFILTER_2		0x1c84
 
-#define RADEON_RB2D_DSTCACHE_CTLSTAT	0x342c
+#define R300_RB2D_DSTCACHE_CTLSTAT	0x342c /* use R300_DSTCACHE_CTLSTAT */
-#	define RADEON_RB2D_DC_FLUSH		(3 << 0)
+#define R300_DSTCACHE_CTLSTAT		0x1714
-#	define RADEON_RB2D_DC_FREE		(3 << 2)
+#	define R300_RB2D_DC_FLUSH		(3 << 0)
-#	define RADEON_RB2D_DC_FLUSH_ALL		0xf
+#	define R300_RB2D_DC_FREE		(3 << 2)
-#	define RADEON_RB2D_DC_BUSY		(1 << 31)
+#	define R300_RB2D_DC_FLUSH_ALL		0xf
+#	define R300_RB2D_DC_BUSY		(1 << 31)
 #define RADEON_RB3D_CNTL		0x1c3c
 #	define RADEON_ALPHA_BLEND_ENABLE	(1 << 0)
 #	define RADEON_PLANE_MASK_ENABLE		(1 << 1)
@@ -643,11 +690,18 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #	define RADEON_RB3D_ZC_FREE		(1 << 2)
 #	define RADEON_RB3D_ZC_FLUSH_ALL		0x5
 #	define RADEON_RB3D_ZC_BUSY		(1 << 31)
+#define R300_ZB_ZCACHE_CTLSTAT                  0x4f18
+#	define R300_ZC_FLUSH		        (1 << 0)
+#	define R300_ZC_FREE		        (1 << 1)
+#	define R300_ZC_FLUSH_ALL		0x3
+#	define R300_ZC_BUSY		        (1 << 31)
 #define RADEON_RB3D_DSTCACHE_CTLSTAT	0x325c
 #	define RADEON_RB3D_DC_FLUSH		(3 << 0)
 #	define RADEON_RB3D_DC_FREE		(3 << 2)
 #	define RADEON_RB3D_DC_FLUSH_ALL		0xf
 #	define RADEON_RB3D_DC_BUSY		(1 << 31)
+#define R300_RB3D_DSTCACHE_CTLSTAT              0x4e4c
+#	define R300_RB3D_DC_FINISH		(1 << 4)
 #define RADEON_RB3D_ZSTENCILCNTL	0x1c2c
 #	define RADEON_Z_TEST_MASK		(7 << 4)
 #	define RADEON_Z_TEST_ALWAYS		(7 << 4)
@@ -1057,6 +1111,31 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 
 #define R200_VAP_PVS_CNTL_1               0x22D0
 
+#define R500_D1CRTC_STATUS 0x609c
+#define R500_D2CRTC_STATUS 0x689c
+#define R500_CRTC_V_BLANK (1<<0)
+
+#define R500_D1CRTC_FRAME_COUNT 0x60a4
+#define R500_D2CRTC_FRAME_COUNT 0x68a4
+
+#define R500_D1MODE_V_COUNTER 0x6530
+#define R500_D2MODE_V_COUNTER 0x6d30
+
+#define R500_D1MODE_VBLANK_STATUS 0x6534
+#define R500_D2MODE_VBLANK_STATUS 0x6d34
+#define R500_VBLANK_OCCURED (1<<0)
+#define R500_VBLANK_ACK     (1<<4)
+#define R500_VBLANK_STAT    (1<<12)
+#define R500_VBLANK_INT     (1<<16)
+
+#define R500_DxMODE_INT_MASK 0x6540
+#define R500_D1MODE_INT_MASK (1<<0)
+#define R500_D2MODE_INT_MASK (1<<8)
+
+#define R500_DISP_INTERRUPT_STATUS 0x7edc
+#define R500_D1_VBLANK_INTERRUPT (1 << 4)
+#define R500_D2_VBLANK_INTERRUPT (1 << 5)
+
 /* Constants */
 #define RADEON_MAX_USEC_TIMEOUT		100000	/* 100 ms */
 
@@ -1078,42 +1157,50 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #define RADEON_READ8(reg)	DRM_READ8(  dev_priv->mmio, (reg) )
 #define RADEON_WRITE8(reg,val)	DRM_WRITE8( dev_priv->mmio, (reg), (val) )
 
-#define RADEON_WRITE_PLL( addr, val )					\
+#define RADEON_WRITE_PLL(addr, val)					\
 do {									\
-	RADEON_WRITE8( RADEON_CLOCK_CNTL_INDEX,				\
+	RADEON_WRITE8(RADEON_CLOCK_CNTL_INDEX,				\
 		       ((addr) & 0x1f) | RADEON_PLL_WR_EN );		\
-	RADEON_WRITE( RADEON_CLOCK_CNTL_DATA, (val) );			\
+	RADEON_WRITE(RADEON_CLOCK_CNTL_DATA, (val));			\
 } while (0)
 
-#define RADEON_WRITE_IGPGART( addr, val )				\
+#define RADEON_WRITE_PCIE(addr, val)					\
 do {									\
-	RADEON_WRITE( RADEON_IGPGART_INDEX,				\
+	RADEON_WRITE8(RADEON_PCIE_INDEX,				\
-			((addr) & 0x7f) | (1 << 8));			\
-	RADEON_WRITE( RADEON_IGPGART_DATA, (val) );			\
-	RADEON_WRITE( RADEON_IGPGART_INDEX, 0x7f );			\
-} while (0)
-
-#define RADEON_WRITE_PCIE( addr, val )					\
-do {									\
-	RADEON_WRITE8( RADEON_PCIE_INDEX,				\
 			((addr) & 0xff));				\
-	RADEON_WRITE( RADEON_PCIE_DATA, (val) );			\
+	RADEON_WRITE(RADEON_PCIE_DATA, (val));			\
 } while (0)
 
-#define RADEON_WRITE_MCIND( addr, val )					\
+#define R500_WRITE_MCIND(addr, val)					\
-	do {								\
+do {								\
 	RADEON_WRITE(R520_MC_IND_INDEX, 0xff0000 | ((addr) & 0xff));	\
 	RADEON_WRITE(R520_MC_IND_DATA, (val));			\
 	RADEON_WRITE(R520_MC_IND_INDEX, 0);	\
-	} while (0)
+} while (0)
 
-#define RS690_WRITE_MCIND( addr, val )					\
+#define RS480_WRITE_MCIND(addr, val)				\
+do {									\
+	RADEON_WRITE(RS480_NB_MC_INDEX,				\
+			((addr) & 0xff) | RS480_NB_MC_IND_WR_EN);	\
+	RADEON_WRITE(RS480_NB_MC_DATA, (val));			\
+	RADEON_WRITE(RS480_NB_MC_INDEX, 0xff);			\
+} while (0)
+
+#define RS690_WRITE_MCIND(addr, val)					\
 do {								\
 	RADEON_WRITE(RS690_MC_INDEX, RS690_MC_INDEX_WR_EN | ((addr) & RS690_MC_INDEX_MASK));	\
 	RADEON_WRITE(RS690_MC_DATA, val);			\
 	RADEON_WRITE(RS690_MC_INDEX, RS690_MC_INDEX_WR_ACK);	\
 } while (0)
 
+#define IGP_WRITE_MCIND(addr, val)				\
+do {									\
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)       \
+		RS690_WRITE_MCIND(addr, val);				\
+	else								\
+		RS480_WRITE_MCIND(addr, val);				\
+} while (0)
+
 #define CP_PACKET0( reg, n )						\
 	(RADEON_CP_PACKET0 | ((n) << 16) | ((reg) >> 2))
 #define CP_PACKET0_TABLE( reg, n )					\
@@ -1154,23 +1241,43 @@ do {								\
 } while (0)
 
 #define RADEON_FLUSH_CACHE() do {					\
-	OUT_RING( CP_PACKET0( RADEON_RB3D_DSTCACHE_CTLSTAT, 0 ) );	\
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) <= CHIP_RV280) {	\
-	OUT_RING( RADEON_RB3D_DC_FLUSH );				\
+		OUT_RING(CP_PACKET0(RADEON_RB3D_DSTCACHE_CTLSTAT, 0));	\
+		OUT_RING(RADEON_RB3D_DC_FLUSH);				\
+	} else {                                                        \
+		OUT_RING(CP_PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));	\
+		OUT_RING(RADEON_RB3D_DC_FLUSH);				\
+	}                                                               \
 } while (0)
 
 #define RADEON_PURGE_CACHE() do {					\
-	OUT_RING( CP_PACKET0( RADEON_RB3D_DSTCACHE_CTLSTAT, 0 ) );	\
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) <= CHIP_RV280) {	\
-	OUT_RING( RADEON_RB3D_DC_FLUSH_ALL );				\
+		OUT_RING(CP_PACKET0(RADEON_RB3D_DSTCACHE_CTLSTAT, 0));	\
+		OUT_RING(RADEON_RB3D_DC_FLUSH_ALL);			\
+	} else {                                                        \
+		OUT_RING(CP_PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));	\
+		OUT_RING(RADEON_RB3D_DC_FLUSH_ALL);			\
+	}                                                               \
 } while (0)
 
 #define RADEON_FLUSH_ZCACHE() do {					\
-	OUT_RING( CP_PACKET0( RADEON_RB3D_ZCACHE_CTLSTAT, 0 ) );	\
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) <= CHIP_RV280) {	\
-	OUT_RING( RADEON_RB3D_ZC_FLUSH );				\
+		OUT_RING(CP_PACKET0(RADEON_RB3D_ZCACHE_CTLSTAT, 0));	\
+		OUT_RING(RADEON_RB3D_ZC_FLUSH);				\
+	} else {                                                        \
+		OUT_RING(CP_PACKET0(R300_ZB_ZCACHE_CTLSTAT, 0));	\
+		OUT_RING(R300_ZC_FLUSH);				\
+	}                                                               \
 } while (0)
 
 #define RADEON_PURGE_ZCACHE() do {					\
-	OUT_RING( CP_PACKET0( RADEON_RB3D_ZCACHE_CTLSTAT, 0 ) );	\
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) <= CHIP_RV280) {	\
-	OUT_RING( RADEON_RB3D_ZC_FLUSH_ALL );				\
+		OUT_RING(CP_PACKET0(RADEON_RB3D_ZCACHE_CTLSTAT, 0));	\
+		OUT_RING(RADEON_RB3D_ZC_FLUSH_ALL);			\
+	} else {                                                        \
+		OUT_RING(CP_PACKET0(R300_RB3D_DSTCACHE_CTLSTAT, 0));	\
+		OUT_RING(R300_ZC_FLUSH_ALL);				\
+	}                                                               \
 } while (0)
 
 /* ================================================================

drivers/char/drm/radeon_irq.c

@@ -234,7 +234,7 @@ int radeon_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_pr
 	return radeon_wait_irq(dev, irqwait->irq_seq);
 }
 
-static void radeon_enable_interrupt(struct drm_device *dev)
+void radeon_enable_interrupt(struct drm_device *dev)
 {
 	drm_radeon_private_t *dev_priv = (drm_radeon_private_t *) dev->dev_private;
 

drivers/char/drm/radeon_state.c

@@ -1662,7 +1662,7 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 	u32 height;
 	int i;
 	u32 texpitch, microtile;
-	u32 offset;
+	u32 offset, byte_offset;
 	RING_LOCALS;
 
 	if (radeon_check_and_fixup_offset(dev_priv, file_priv, &tex->offset)) {
@@ -1727,6 +1727,13 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 	} else
 		microtile = 0;
 
+	/* this might fail for zero-sized uploads - are those illegal? */
+	if (!radeon_check_offset(dev_priv, tex->offset + image->height *
+				blit_width - 1)) {
+		DRM_ERROR("Invalid final destination offset\n");
+		return -EINVAL;
+	}
+
 	DRM_DEBUG("tex=%dx%d blit=%d\n", tex_width, tex->height, blit_width);
 
 	do {
@@ -1840,6 +1847,7 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 		}
 
 #undef RADEON_COPY_MT
+		byte_offset = (image->y & ~2047) * blit_width;
 		buf->file_priv = file_priv;
 		buf->used = size;
 		offset = dev_priv->gart_buffers_offset + buf->offset;
@@ -1854,9 +1862,9 @@ static int radeon_cp_dispatch_texture(struct drm_device * dev,
 			 RADEON_DP_SRC_SOURCE_MEMORY |
 			 RADEON_GMC_CLR_CMP_CNTL_DIS | RADEON_GMC_WR_MSK_DIS);
 		OUT_RING((spitch << 22) | (offset >> 10));
-		OUT_RING((texpitch << 22) | (tex->offset >> 10));
+		OUT_RING((texpitch << 22) | ((tex->offset >> 10) + (byte_offset >> 10)));
 		OUT_RING(0);
-		OUT_RING((image->x << 16) | image->y);
+		OUT_RING((image->x << 16) | (image->y % 2048));
 		OUT_RING((image->width << 16) | height);
 		RADEON_WAIT_UNTIL_2D_IDLE();
 		ADVANCE_RING();
@@ -3037,6 +3045,9 @@ static int radeon_cp_getparam(struct drm_device *dev, void *data, struct drm_fil
 	case RADEON_PARAM_FB_LOCATION:
 		value = radeon_read_fb_location(dev_priv);
 		break;
+	case RADEON_PARAM_NUM_GB_PIPES:
+		value = dev_priv->num_gb_pipes;
+		break;
 	default:
 		DRM_DEBUG("Invalid parameter %d\n", param->param);
 		return -EINVAL;

drivers/char/tty_ioctl.c

@@ -981,16 +981,9 @@ EXPORT_SYMBOL_GPL(tty_perform_flush);
 int n_tty_ioctl(struct tty_struct *tty, struct file *file,
 		       unsigned int cmd, unsigned long arg)
 {
-	struct tty_struct *real_tty;
 	unsigned long flags;
 	int retval;
 
-	if (tty->driver->type == TTY_DRIVER_TYPE_PTY &&
-	    tty->driver->subtype == PTY_TYPE_MASTER)
-		real_tty = tty->link;
-	else
-		real_tty = tty;
-
 	switch (cmd) {
 	case TCXONC:
 		retval = tty_check_change(tty);

drivers/firewire/Kconfig

@@ -1,28 +1,26 @@
-comment "An alternative FireWire stack is available with EXPERIMENTAL=y"
+comment "A new alternative FireWire stack is available with EXPERIMENTAL=y"
 	depends on EXPERIMENTAL=n
 
+comment "Enable only one of the two stacks, unless you know what you are doing"
+	depends on EXPERIMENTAL
+
 config FIREWIRE
-	tristate "IEEE 1394 (FireWire) support - alternative stack, EXPERIMENTAL"
+	tristate "New FireWire stack, EXPERIMENTAL"
 	depends on EXPERIMENTAL
 	select CRC_ITU_T
 	help
 	  This is the "Juju" FireWire stack, a new alternative implementation
 	  designed for robustness and simplicity.  You can build either this
-	  stack, or the classic stack (the ieee1394 driver, ohci1394 etc.)
+	  stack, or the old stack (the ieee1394 driver, ohci1394 etc.) or both.
-	  or both.  Please read http://wiki.linux1394.org/JujuMigration before
+	  Please read http://wiki.linux1394.org/JujuMigration before you
-	  you enable the new stack.
+	  enable the new stack.
 
 	  To compile this driver as a module, say M here: the module will be
 	  called firewire-core.  It functionally replaces ieee1394, raw1394,
 	  and video1394.
 
-          NOTE:
-
-	  You should only build ONE of the stacks, unless you REALLY know what
-	  you are doing.
-
 config FIREWIRE_OHCI
-	tristate "Support for OHCI FireWire host controllers"
+	tristate "OHCI-1394 controllers"
 	depends on PCI && FIREWIRE
 	help
 	  Enable this driver if you have a FireWire controller based
@@ -35,10 +33,10 @@ config FIREWIRE_OHCI
 
 	  NOTE:
 
-	  You should only build ohci1394 or firewire-ohci, but not both.
+	  You should only build either firewire-ohci or the old ohci1394 driver,
-	  If you nevertheless want to install both, you should configure them
+	  but not both.  If you nevertheless want to install both, you should
-	  only as modules and blacklist the driver(s) which you don't want to
+	  configure them only as modules and blacklist the driver(s) which you
-	  have auto-loaded.  Add either
+	  don't want to have auto-loaded.  Add either
 
 	      blacklist firewire-ohci
 	  or
@@ -60,7 +58,7 @@ config FIREWIRE_OHCI_DEBUG
 	default y
 
 config FIREWIRE_SBP2
-	tristate "Support for storage devices (SBP-2 protocol driver)"
+	tristate "Storage devices (SBP-2 protocol)"
 	depends on FIREWIRE && SCSI
 	help
 	  This option enables you to use SBP-2 devices connected to a

drivers/firewire/fw-cdev.c

@@ -205,6 +205,7 @@ fw_device_op_read(struct file *file,
 	return dequeue_event(client, buffer, count);
 }
 
+/* caller must hold card->lock so that node pointers can be dereferenced here */
 static void
 fill_bus_reset_event(struct fw_cdev_event_bus_reset *event,
 		     struct client *client)
@@ -214,7 +215,6 @@ fill_bus_reset_event(struct fw_cdev_event_bus_reset *event,
 	event->closure	     = client->bus_reset_closure;
 	event->type          = FW_CDEV_EVENT_BUS_RESET;
 	event->generation    = client->device->generation;
-	smp_rmb();           /* node_id must not be older than generation */
 	event->node_id       = client->device->node_id;
 	event->local_node_id = card->local_node->node_id;
 	event->bm_node_id    = 0; /* FIXME: We don't track the BM. */
@@ -274,6 +274,7 @@ static int ioctl_get_info(struct client *client, void *buffer)
 {
 	struct fw_cdev_get_info *get_info = buffer;
 	struct fw_cdev_event_bus_reset bus_reset;
+	struct fw_card *card = client->device->card;
 	unsigned long ret = 0;
 
 	client->version = get_info->version;
@@ -299,13 +300,17 @@ static int ioctl_get_info(struct client *client, void *buffer)
 	client->bus_reset_closure = get_info->bus_reset_closure;
 	if (get_info->bus_reset != 0) {
 		void __user *uptr = u64_to_uptr(get_info->bus_reset);
+		unsigned long flags;
 
+		spin_lock_irqsave(&card->lock, flags);
 		fill_bus_reset_event(&bus_reset, client);
+		spin_unlock_irqrestore(&card->lock, flags);
+
 		if (copy_to_user(uptr, &bus_reset, sizeof(bus_reset)))
 			return -EFAULT;
 	}
 
-	get_info->card = client->device->card->index;
+	get_info->card = card->index;
 
 	return 0;
 }

drivers/firewire/fw-ohci.c

@@ -265,9 +265,7 @@ static void log_irqs(u32 evt)
 	    !(evt & OHCI1394_busReset))
 		return;
 
-	printk(KERN_DEBUG KBUILD_MODNAME ": IRQ "
+	fw_notify("IRQ %08x%s%s%s%s%s%s%s%s%s%s%s%s%s\n", evt,
-	       "%08x%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
-	       evt,
 	    evt & OHCI1394_selfIDComplete	? " selfID"		: "",
 	    evt & OHCI1394_RQPkt		? " AR_req"		: "",
 	    evt & OHCI1394_RSPkt		? " AR_resp"		: "",
@@ -308,20 +306,19 @@ static void log_selfids(int node_id, int generation, int self_id_count, u32 *s)
 	if (likely(!(param_debug & OHCI_PARAM_DEBUG_SELFIDS)))
 		return;
 
-	printk(KERN_DEBUG KBUILD_MODNAME ": %d selfIDs, generation %d, "
+	fw_notify("%d selfIDs, generation %d, local node ID %04x\n",
-	       "local node ID %04x\n", self_id_count, generation, node_id);
+		  self_id_count, generation, node_id);
 
 	for (; self_id_count--; ++s)
 		if ((*s & 1 << 23) == 0)
-			printk(KERN_DEBUG "selfID 0: %08x, phy %d [%c%c%c] "
+			fw_notify("selfID 0: %08x, phy %d [%c%c%c] "
 			    "%s gc=%d %s %s%s%s\n",
 			    *s, *s >> 24 & 63, _p(s, 6), _p(s, 4), _p(s, 2),
 			    speed[*s >> 14 & 3], *s >> 16 & 63,
 			    power[*s >> 8 & 7], *s >> 22 & 1 ? "L" : "",
 			    *s >> 11 & 1 ? "c" : "", *s & 2 ? "i" : "");
 		else
-			printk(KERN_DEBUG "selfID n: %08x, phy %d "
+			fw_notify("selfID n: %08x, phy %d [%c%c%c%c%c%c%c%c]\n",
-			       "[%c%c%c%c%c%c%c%c]\n",
 			    *s, *s >> 24 & 63,
 			    _p(s, 16), _p(s, 14), _p(s, 12), _p(s, 10),
 			    _p(s,  8), _p(s,  6), _p(s,  4), _p(s,  2));
@@ -373,15 +370,14 @@ static void log_ar_at_event(char dir, int speed, u32 *header, int evt)
 			evt = 0x1f;
 
 	if (evt == OHCI1394_evt_bus_reset) {
-		printk(KERN_DEBUG "A%c evt_bus_reset, generation %d\n",
+		fw_notify("A%c evt_bus_reset, generation %d\n",
 		    dir, (header[2] >> 16) & 0xff);
 		return;
 	}
 
 	if (header[0] == ~header[1]) {
-		printk(KERN_DEBUG "A%c %s, %s, %08x\n",
+		fw_notify("A%c %s, %s, %08x\n",
-		       dir, evts[evt], phys[header[0] >> 30 & 0x3],
+		    dir, evts[evt], phys[header[0] >> 30 & 0x3], header[0]);
-		       header[0]);
 		return;
 	}
 
@@ -400,11 +396,10 @@ static void log_ar_at_event(char dir, int speed, u32 *header, int evt)
 
 	switch (tcode) {
 	case 0xe: case 0xa:
-		printk(KERN_DEBUG "A%c %s, %s\n",
+		fw_notify("A%c %s, %s\n", dir, evts[evt], tcodes[tcode]);
-		       dir, evts[evt], tcodes[tcode]);
 		break;
 	case 0x0: case 0x1: case 0x4: case 0x5: case 0x9:
-		printk(KERN_DEBUG "A%c spd %x tl %02x, "
+		fw_notify("A%c spd %x tl %02x, "
 		    "%04x -> %04x, %s, "
 		    "%s, %04x%08x%s\n",
 		    dir, speed, header[0] >> 10 & 0x3f,
@@ -412,7 +407,7 @@ static void log_ar_at_event(char dir, int speed, u32 *header, int evt)
 		    tcodes[tcode], header[1] & 0xffff, header[2], specific);
 		break;
 	default:
-		printk(KERN_DEBUG "A%c spd %x tl %02x, "
+		fw_notify("A%c spd %x tl %02x, "
 		    "%04x -> %04x, %s, "
 		    "%s%s\n",
 		    dir, speed, header[0] >> 10 & 0x3f,
@@ -548,6 +543,11 @@ static __le32 *handle_ar_packet(struct ar_context *ctx, __le32 *buffer)
 		p.header_length = 12;
 		p.payload_length = 0;
 		break;
+
+	default:
+		/* FIXME: Stop context, discard everything, and restart? */
+		p.header_length = 0;
+		p.payload_length = 0;
 	}
 
 	p.payload = (void *) buffer + p.header_length;
@@ -1468,6 +1468,9 @@ static int ohci_enable(struct fw_card *card, u32 *config_rom, size_t length)
 	reg_write(ohci, OHCI1394_HCControlClear,
 		  OHCI1394_HCControl_noByteSwapData);
 
+	reg_write(ohci, OHCI1394_SelfIDBuffer, ohci->self_id_bus);
+	reg_write(ohci, OHCI1394_LinkControlClear,
+		  OHCI1394_LinkControl_rcvPhyPkt);
 	reg_write(ohci, OHCI1394_LinkControlSet,
 		  OHCI1394_LinkControl_rcvSelfID |
 		  OHCI1394_LinkControl_cycleTimerEnable |
@@ -1481,7 +1484,6 @@ static int ohci_enable(struct fw_card *card, u32 *config_rom, size_t length)
 	ar_context_run(&ohci->ar_request_ctx);
 	ar_context_run(&ohci->ar_response_ctx);
 
-	reg_write(ohci, OHCI1394_SelfIDBuffer, ohci->self_id_bus);
 	reg_write(ohci, OHCI1394_PhyUpperBound, 0x00010000);
 	reg_write(ohci, OHCI1394_IntEventClear, ~0);
 	reg_write(ohci, OHCI1394_IntMaskClear, ~0);

drivers/firewire/fw-transaction.c

@@ -20,6 +20,7 @@
 
 #include <linux/completion.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -297,37 +298,55 @@ EXPORT_SYMBOL(fw_send_request);
 struct fw_phy_packet {
 	struct fw_packet packet;
 	struct completion done;
+	struct kref kref;
 };
 
-static void
+static void phy_packet_release(struct kref *kref)
-transmit_phy_packet_callback(struct fw_packet *packet,
+{
+	struct fw_phy_packet *p =
+			container_of(kref, struct fw_phy_packet, kref);
+	kfree(p);
+}
+
+static void transmit_phy_packet_callback(struct fw_packet *packet,
 					 struct fw_card *card, int status)
 {
 	struct fw_phy_packet *p =
 			container_of(packet, struct fw_phy_packet, packet);
 
 	complete(&p->done);
+	kref_put(&p->kref, phy_packet_release);
 }
 
 void fw_send_phy_config(struct fw_card *card,
 			int node_id, int generation, int gap_count)
 {
-	struct fw_phy_packet p;
+	struct fw_phy_packet *p;
+	long timeout = DIV_ROUND_UP(HZ, 10);
 	u32 data = PHY_IDENTIFIER(PHY_PACKET_CONFIG) |
 		   PHY_CONFIG_ROOT_ID(node_id) |
 		   PHY_CONFIG_GAP_COUNT(gap_count);
 
-	p.packet.header[0] = data;
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
-	p.packet.header[1] = ~data;
+	if (p == NULL)
-	p.packet.header_length = 8;
+		return;
-	p.packet.payload_length = 0;
-	p.packet.speed = SCODE_100;
-	p.packet.generation = generation;
-	p.packet.callback = transmit_phy_packet_callback;
-	init_completion(&p.done);
 
-	card->driver->send_request(card, &p.packet);
+	p->packet.header[0] = data;
-	wait_for_completion(&p.done);
+	p->packet.header[1] = ~data;
+	p->packet.header_length = 8;
+	p->packet.payload_length = 0;
+	p->packet.speed = SCODE_100;
+	p->packet.generation = generation;
+	p->packet.callback = transmit_phy_packet_callback;
+	init_completion(&p->done);
+	kref_set(&p->kref, 2);
+
+	card->driver->send_request(card, &p->packet);
+	timeout = wait_for_completion_timeout(&p->done, timeout);
+	kref_put(&p->kref, phy_packet_release);
+
+	/* will leak p if the callback is never executed */
+	WARN_ON(timeout == 0);
 }
 
 void fw_flush_transactions(struct fw_card *card)
@@ -572,7 +591,8 @@ allocate_request(struct fw_packet *p)
 		break;
 
 	default:
-		BUG();
+		fw_error("ERROR - corrupt request received - %08x %08x %08x\n",
+			 p->header[0], p->header[1], p->header[2]);
 		return NULL;
 	}
 

drivers/hwmon/abituguru3.c

@@ -30,6 +30,7 @@
 #include <linux/platform_device.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/dmi.h>
 #include <asm/io.h>
 
 /* uGuru3 bank addresses */
@@ -323,7 +324,7 @@ static const struct abituguru3_motherboard_info abituguru3_motherboards[] = {
 		{ "AUX1 Fan",		36, 2, 60, 1, 0 },
 		{ NULL, 0, 0, 0, 0, 0 } }
 	},
-	{ 0x0013, "unknown", {
+	{ 0x0013, "Abit AW8D", {
 		{ "CPU Core",		 0, 0, 10, 1, 0 },
 		{ "DDR",		 1, 0, 10, 1, 0 },
 		{ "DDR VTT",		 2, 0, 10, 1, 0 },
@@ -349,6 +350,7 @@ static const struct abituguru3_motherboard_info abituguru3_motherboards[] = {
 		{ "AUX2 Fan",		36, 2, 60, 1, 0 },
 		{ "AUX3 Fan",		37, 2, 60, 1, 0 },
 		{ "AUX4 Fan",		38, 2, 60, 1, 0 },
+		{ "AUX5 Fan",		39, 2, 60, 1, 0 },
 		{ NULL, 0, 0, 0, 0, 0 } }
 	},
 	{ 0x0014, "Abit AB9 Pro", {
@@ -1111,11 +1113,12 @@ static int __init abituguru3_detect(void)
 {
 	/* See if there is an uguru3 there. An idle uGuru3 will hold 0x00 or
 	   0x08 at DATA and 0xAC at CMD. Sometimes the uGuru3 will hold 0x05
-	   at CMD instead, why is unknown. So we test for 0x05 too. */
+	   or 0x55 at CMD instead, why is unknown. */
 	u8 data_val = inb_p(ABIT_UGURU3_BASE + ABIT_UGURU3_DATA);
 	u8 cmd_val = inb_p(ABIT_UGURU3_BASE + ABIT_UGURU3_CMD);
 	if (((data_val == 0x00) || (data_val == 0x08)) &&
-			((cmd_val == 0xAC) || (cmd_val == 0x05)))
+			((cmd_val == 0xAC) || (cmd_val == 0x05) ||
+			 (cmd_val == 0x55)))
 		return ABIT_UGURU3_BASE;
 
 	ABIT_UGURU3_DEBUG("no Abit uGuru3 found, data = 0x%02X, cmd = "
@@ -1138,6 +1141,15 @@ static int __init abituguru3_init(void)
 	int address, err;
 	struct resource res = { .flags = IORESOURCE_IO };
 
+#ifdef CONFIG_DMI
+	const char *board_vendor = dmi_get_system_info(DMI_BOARD_VENDOR);
+
+	/* safety check, refuse to load on non Abit motherboards */
+	if (!force && (!board_vendor ||
+			strcmp(board_vendor, "http://www.abit.com.tw/")))
+		return -ENODEV;
+#endif
+
 	address = abituguru3_detect();
 	if (address < 0)
 		return address;

drivers/hwmon/adt7473.c

@@ -309,6 +309,9 @@ no_sensor_update:
 						ADT7473_REG_PWM_BHVR(i));
 	}
 
+	i = i2c_smbus_read_byte_data(client, ADT7473_REG_CFG4);
+	data->max_duty_at_overheat = !!(i & ADT7473_CFG4_MAX_DUTY_AT_OVT);
+
 	data->limits_last_updated = local_jiffies;
 	data->limits_valid = 1;
 

drivers/hwmon/lm75.c

@@ -251,10 +251,13 @@ static int lm75_detach_client(struct i2c_client *client)
    the SMBus standard. */
 static int lm75_read_value(struct i2c_client *client, u8 reg)
 {
+	int value;
+
 	if (reg == LM75_REG_CONF)
 		return i2c_smbus_read_byte_data(client, reg);
-	else
+
-		return swab16(i2c_smbus_read_word_data(client, reg));
+	value = i2c_smbus_read_word_data(client, reg);
+	return (value < 0) ? value : swab16(value);
 }
 
 static int lm75_write_value(struct i2c_client *client, u8 reg, u16 value)
@@ -287,9 +290,16 @@ static struct lm75_data *lm75_update_device(struct device *dev)
 		int i;
 		dev_dbg(&client->dev, "Starting lm75 update\n");
 
-		for (i = 0; i < ARRAY_SIZE(data->temp); i++)
+		for (i = 0; i < ARRAY_SIZE(data->temp); i++) {
-			data->temp[i] = lm75_read_value(client,
+			int status;
-							LM75_REG_TEMP[i]);
+
+			status = lm75_read_value(client, LM75_REG_TEMP[i]);
+			if (status < 0)
+				dev_dbg(&client->dev, "reg %d, err %d\n",
+						LM75_REG_TEMP[i], status);
+			else
+				data->temp[i] = status;
+		}
 		data->last_updated = jiffies;
 		data->valid = 1;
 	}

drivers/hwmon/lm85.c

@@ -192,23 +192,20 @@ static int RANGE_TO_REG( int range )
 {
 	int i;
 
-	if ( range < lm85_range_map[0] ) { 
+	if (range >= lm85_range_map[15])
-		return 0 ;
-	} else if ( range > lm85_range_map[15] ) {
 		return 15 ;
-	} else {  /* find closest match */
+
-		for ( i = 14 ; i >= 0 ; --i ) {
+	/* Find the closest match */
-			if ( range > lm85_range_map[i] ) { /* range bracketed */
+	for (i = 14; i >= 0; --i) {
-				if ((lm85_range_map[i+1] - range) < 
+		if (range >= lm85_range_map[i]) {
-					(range - lm85_range_map[i])) {
+			if ((lm85_range_map[i + 1] - range) <
-					i++;
+					(range - lm85_range_map[i]))
-					break;
+				return i + 1;
-				}
+			return i;
-				break;
 		}
 	}
-	}
+
-	return( i & 0x0f );
+	return 0;
 }
 #define RANGE_FROM_REG(val) (lm85_range_map[(val)&0x0f])
 

drivers/ide/Kconfig

@@ -823,13 +823,6 @@ config BLK_DEV_IDE_RAPIDE
 	  Say Y here if you want to support the Yellowstone RapIDE controller
 	  manufactured for use with Acorn computers.
 
-config BLK_DEV_IDE_BAST
-	tristate "Simtec BAST / Thorcom VR1000 IDE support"
-	depends on ARM && (ARCH_BAST || MACH_VR1000)
-	help
-	  Say Y here if you want to support the onboard IDE channels on the
-	  Simtec BAST or the Thorcom VR1000
-
 config IDE_H8300
 	tristate "H8300 IDE support"
 	depends on H8300

drivers/ide/arm/Makefile

@@ -1,7 +1,6 @@
 
 obj-$(CONFIG_BLK_DEV_IDE_ICSIDE)	+= icside.o
 obj-$(CONFIG_BLK_DEV_IDE_RAPIDE)	+= rapide.o
-obj-$(CONFIG_BLK_DEV_IDE_BAST)		+= bast-ide.o
 obj-$(CONFIG_BLK_DEV_PALMCHIP_BK3710)	+= palm_bk3710.o
 
 ifeq ($(CONFIG_IDE_ARM), m)

drivers/ide/arm/bast-ide.c

@@ -1,90 +0,0 @@
-/*
- * Copyright (c) 2003-2004 Simtec Electronics
- *  Ben Dooks <ben@simtec.co.uk>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/ide.h>
-#include <linux/init.h>
-
-#include <asm/mach-types.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/arch/map.h>
-#include <asm/arch/bast-map.h>
-#include <asm/arch/bast-irq.h>
-
-#define DRV_NAME "bast-ide"
-
-static int __init bastide_register(unsigned int base, unsigned int aux, int irq)
-{
-	ide_hwif_t *hwif;
-	hw_regs_t hw;
-	int i;
-	u8 idx[4] = { 0xff, 0xff, 0xff, 0xff };
-
-	memset(&hw, 0, sizeof(hw));
-
-	base += BAST_IDE_CS;
-	aux  += BAST_IDE_CS;
-
-	for (i = 0; i <= 7; i++) {
-		hw.io_ports_array[i] = (unsigned long)base;
-		base += 0x20;
-	}
-
-	hw.io_ports.ctl_addr = aux + (6 * 0x20);
-	hw.irq = irq;
-	hw.chipset = ide_generic;
-
-	hwif = ide_find_port();
-	if (hwif == NULL)
-		goto out;
-
-	i = hwif->index;
-
-	ide_init_port_data(hwif, i);
-	ide_init_port_hw(hwif, &hw);
-	hwif->port_ops = NULL;
-
-	idx[0] = i;
-
-	ide_device_add(idx, NULL);
-out:
-	return 0;
-}
-
-static int __init bastide_init(void)
-{
-	unsigned long base = BAST_VA_IDEPRI + BAST_IDE_CS;
-
-	/* we can treat the VR1000 and the BAST the same */
-
-	if (!(machine_is_bast() || machine_is_vr1000()))
-		return 0;
-
-	printk("BAST: IDE driver, (c) 2003-2004 Simtec Electronics\n");
-
-	if (!request_mem_region(base, 0x400000, DRV_NAME)) {
-		printk(KERN_ERR "%s: resources busy\n", DRV_NAME);
-		return -EBUSY;
-	}
-
-	bastide_register(BAST_VA_IDEPRI, BAST_VA_IDEPRIAUX, IRQ_IDE0);
-	bastide_register(BAST_VA_IDESEC, BAST_VA_IDESECAUX, IRQ_IDE1);
-
-	return 0;
-}
-
-module_init(bastide_init);
-
-MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Simtec BAST / Thorcom VR1000 IDE driver");

drivers/ide/arm/palm_bk3710.c

@@ -353,8 +353,8 @@ static int __devinit palm_bk3710_probe(struct platform_device *pdev)
 	struct clk *clkp;
 	struct resource *mem, *irq;
 	ide_hwif_t *hwif;
-	void __iomem *base;
+	unsigned long base;
-	int pribase, i;
+	int i;
 	hw_regs_t hw;
 	u8 idx[4] = { 0xff, 0xff, 0xff, 0xff };
 
@@ -374,22 +374,27 @@ static int __devinit palm_bk3710_probe(struct platform_device *pdev)
 		printk(KERN_ERR "failed to get memory region resource\n");
 		return -ENODEV;
 	}
+
 	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (irq == NULL) {
 		printk(KERN_ERR "failed to get IRQ resource\n");
 		return -ENODEV;
 	}
 
-	base = (void *)mem->start;
+	if (request_mem_region(mem->start, mem->end - mem->start + 1,
+			       "palm_bk3710") == NULL) {
+		printk(KERN_ERR "failed to request memory region\n");
+		return -EBUSY;
+	}
+
+	base = IO_ADDRESS(mem->start);
 
 	/* Configure the Palm Chip controller */
-	palm_bk3710_chipinit(base);
+	palm_bk3710_chipinit((void __iomem *)base);
 
-	pribase = mem->start + IDE_PALM_ATA_PRI_REG_OFFSET;
 	for (i = 0; i < IDE_NR_PORTS - 2; i++)
-		hw.io_ports_array[i] = pribase + i;
+		hw.io_ports_array[i] = base + IDE_PALM_ATA_PRI_REG_OFFSET + i;
-	hw.io_ports.ctl_addr = mem->start +
+	hw.io_ports.ctl_addr = base + IDE_PALM_ATA_PRI_CTL_OFFSET;
-			IDE_PALM_ATA_PRI_CTL_OFFSET;
 	hw.irq = irq->start;
 	hw.chipset = ide_palm3710;
 
@@ -434,4 +439,3 @@ static int __init palm_bk3710_init(void)
 
 module_init(palm_bk3710_init);
 MODULE_LICENSE("GPL");
-

drivers/ide/ide-taskfile.c

@@ -225,10 +225,10 @@ static u8 wait_drive_not_busy(ide_drive_t *drive)
 	u8 stat;
 
 	/*
-	 * Last sector was transfered, wait until drive is ready.
+	 * Last sector was transfered, wait until device is ready.  This can
-	 * This can take up to 10 usec, but we will wait max 1 ms.
+	 * take up to 6 ms on some ATAPI devices, so we will wait max 10 ms.
 	 */
-	for (retries = 0; retries < 100; retries++) {
+	for (retries = 0; retries < 1000; retries++) {
 		stat = ide_read_status(drive);
 
 		if (stat & BUSY_STAT)

drivers/ide/legacy/ide-cs.c

@@ -410,6 +410,7 @@ static struct pcmcia_device_id ide_ids[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x001c, 0x0001),	/* Mitsubishi CFA */
 	PCMCIA_DEVICE_MANF_CARD(0x0032, 0x0704),
 	PCMCIA_DEVICE_MANF_CARD(0x0045, 0x0401),	/* SanDisk CFA */
+	PCMCIA_DEVICE_MANF_CARD(0x004f, 0x0000),	/* Kingston */
 	PCMCIA_DEVICE_MANF_CARD(0x0098, 0x0000),	/* Toshiba */
 	PCMCIA_DEVICE_MANF_CARD(0x00a4, 0x002d),
 	PCMCIA_DEVICE_MANF_CARD(0x00ce, 0x0000),	/* Samsung */
@@ -439,6 +440,7 @@ static struct pcmcia_device_id ide_ids[] = {
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "PCIDE", 0x547e66dc, 0x5c5ab149),
 	PCMCIA_DEVICE_PROD_ID12("IO DATA", "PCIDEII", 0x547e66dc, 0xb3662674),
 	PCMCIA_DEVICE_PROD_ID12("LOOKMEET", "CBIDE2      ", 0xe37be2b5, 0x8671043b),
+	PCMCIA_DEVICE_PROD_ID12("M-Systems", "CF300", 0x7ed2ad87, 0x7e9e78ee),
 	PCMCIA_DEVICE_PROD_ID12("M-Systems", "CF500", 0x7ed2ad87, 0x7a13045c),
 	PCMCIA_DEVICE_PROD_ID2("NinjaATA-", 0xebe0bd79),
 	PCMCIA_DEVICE_PROD_ID12("PCMCIA", "CD-ROM", 0x281f1c5d, 0x66536591),
@@ -449,6 +451,7 @@ static struct pcmcia_device_id ide_ids[] = {
 	PCMCIA_DEVICE_PROD_ID12("SMI VENDOR", "SMI PRODUCT", 0x30896c92, 0x703cc5f6),
 	PCMCIA_DEVICE_PROD_ID12("TOSHIBA", "MK2001MPL", 0xb4585a1a, 0x3489e003),
 	PCMCIA_DEVICE_PROD_ID1("TRANSCEND    512M   ", 0xd0909443),
+	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF45", 0x709b1bf1, 0xf68b6f32),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS1GCF80", 0x709b1bf1, 0x2a54d4b1),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS2GCF120", 0x709b1bf1, 0x969aa4f2),
 	PCMCIA_DEVICE_PROD_ID12("TRANSCEND", "TS4GCF120", 0x709b1bf1, 0xf54a91c8),

drivers/ieee1394/Kconfig

@@ -4,7 +4,7 @@ menu "IEEE 1394 (FireWire) support"
 source "drivers/firewire/Kconfig"
 
 config IEEE1394
-	tristate "IEEE 1394 (FireWire) support"
+	tristate "Stable FireWire stack"
 	depends on PCI || BROKEN
 	help
 	  IEEE 1394 describes a high performance serial bus, which is also
@@ -19,30 +19,45 @@ config IEEE1394
 	  To compile this driver as a module, say M here: the
 	  module will be called ieee1394.
 
-comment "Subsystem Options"
+config IEEE1394_OHCI1394
-	depends on IEEE1394
+	tristate "OHCI-1394 controllers"
-
+	depends on PCI && IEEE1394
-config IEEE1394_VERBOSEDEBUG
-	bool "Excessive debugging output"
-	depends on IEEE1394
 	help
-	  If you say Y here, you will get very verbose debugging logs from
+	  Enable this driver if you have an IEEE 1394 controller based on the
-	  the subsystem which includes a dump of the header of every sent
+	  OHCI-1394 specification. The current driver is only tested with OHCI
-	  and received packet.  This can amount to a high amount of data
+	  chipsets made by Texas Instruments and NEC. Most third-party vendors
-	  collected in a very short time which is usually also saved to
+	  use one of these chipsets.  It should work with any OHCI-1394
-	  disk by the system logging daemons.
+	  compliant card, however.
 
-	  Say Y if you really want or need the debugging output, everyone
+	  To compile this driver as a module, say M here: the
-	  else says N.
+	  module will be called ohci1394.
 
-comment "Controllers"
+	  NOTE:
-	depends on IEEE1394
 
-comment "Texas Instruments PCILynx requires I2C"
+	  You should only build either ohci1394 or the new firewire-ohci driver,
+	  but not both.  If you nevertheless want to install both, you should
+	  configure them only as modules and blacklist the driver(s) which you
+	  don't want to have auto-loaded.  Add either
+
+	      blacklist firewire-ohci
+	  or
+	      blacklist ohci1394
+	      blacklist video1394
+	      blacklist dv1394
+
+	  to /etc/modprobe.conf or /etc/modprobe.d/* and update modprobe.conf
+	  depending on your distribution.  The latter two modules should be
+	  blacklisted together with ohci1394 because they depend on ohci1394.
+
+	  If you have an old modprobe which doesn't implement the blacklist
+	  directive, use "install modulename /bin/true" for the modules to be
+	  blacklisted.
+
+comment "PCILynx controller requires I2C"
 	depends on IEEE1394 && I2C=n
 
 config IEEE1394_PCILYNX
-	tristate "Texas Instruments PCILynx support"
+	tristate "PCILynx controller"
 	depends on PCI && IEEE1394 && I2C
 	select I2C_ALGOBIT
 	help
@@ -57,35 +72,11 @@ config IEEE1394_PCILYNX
 	  PowerMacs G3 B&W contain the PCILynx controller.  Therefore
 	  almost everybody can say N here.
 
-config IEEE1394_OHCI1394
-	tristate "OHCI-1394 support"
-	depends on PCI && IEEE1394
-	help
-	  Enable this driver if you have an IEEE 1394 controller based on the
-	  OHCI-1394 specification. The current driver is only tested with OHCI
-	  chipsets made by Texas Instruments and NEC. Most third-party vendors
-	  use one of these chipsets.  It should work with any OHCI-1394
-	  compliant card, however.
-
-	  To compile this driver as a module, say M here: the
-	  module will be called ohci1394.
-
-comment "Protocols"
-	depends on IEEE1394
-
-config IEEE1394_VIDEO1394
-	tristate "OHCI-1394 Video support"
-	depends on IEEE1394 && IEEE1394_OHCI1394
-	help
-	  This option enables video device usage for OHCI-1394 cards.  Enable
-	  this option only if you have an IEEE 1394 video device connected to
-	  an OHCI-1394 card.
-
 comment "SBP-2 support (for storage devices) requires SCSI"
 	depends on IEEE1394 && SCSI=n
 
 config IEEE1394_SBP2
-	tristate "SBP-2 support (Harddisks etc.)"
+	tristate "Storage devices (SBP-2 protocol)"
 	depends on IEEE1394 && SCSI
 	help
 	  This option enables you to use SBP-2 devices connected to an IEEE
@@ -127,24 +118,47 @@ config IEEE1394_ETH1394
 
 	  The module is called eth1394 although it does not emulate Ethernet.
 
+config IEEE1394_RAWIO
+	tristate "raw1394 userspace interface"
+	depends on IEEE1394
+	help
+	  This option adds support for the raw1394 device file which enables
+	  direct communication of user programs with IEEE 1394 devices
+	  (isochronous and asynchronous).  Almost all application programs
+	  which access FireWire require this option.
+
+	  To compile this driver as a module, say M here: the module will be
+	  called raw1394.
+
+config IEEE1394_VIDEO1394
+	tristate "video1394 userspace interface"
+	depends on IEEE1394 && IEEE1394_OHCI1394
+	help
+	  This option adds support for the video1394 device files which enable
+	  isochronous communication of user programs with IEEE 1394 devices,
+	  especially video capture or export.  This interface is used by all
+	  libdc1394 based programs and by several other programs, in addition to
+	  the raw1394 interface.  It is generally not required for DV capture.
+
+	  To compile this driver as a module, say M here: the module will be
+	  called video1394.
+
 config IEEE1394_DV1394
-	tristate "OHCI-DV I/O support (deprecated)"
+	tristate "dv1394 userspace interface (deprecated)"
 	depends on IEEE1394 && IEEE1394_OHCI1394
 	help
 	  The dv1394 driver is unsupported and may be removed from Linux in a
 	  future release.  Its functionality is now provided by raw1394 together
 	  with libraries such as libiec61883.
 
-config IEEE1394_RAWIO
+config IEEE1394_VERBOSEDEBUG
-	tristate "Raw IEEE1394 I/O support"
+	bool "Excessive debugging output"
 	depends on IEEE1394
 	help
-	  This option adds support for the raw1394 device file which enables
+	  If you say Y here, you will get very verbose debugging logs from the
-	  direct communication of user programs with the IEEE 1394 bus and thus
+	  ieee1394 drivers, including sent and received packet headers.  This
-	  with the attached peripherals.  Almost all application programs which
+	  will quickly result in large amounts of data sent to the system log.
-	  access FireWire require this option.
 
-	  To compile this driver as a module, say M here: the module will be
+	  Say Y if you really need the debugging output.  Everyone else says N.
-	  called raw1394.
 
 endmenu

drivers/infiniband/hw/mthca/mthca_memfree.c

@@ -109,7 +109,11 @@ static int mthca_alloc_icm_pages(struct scatterlist *mem, int order, gfp_t gfp_m
 {
 	struct page *page;
 
-	page = alloc_pages(gfp_mask, order);
+	/*
+	 * Use __GFP_ZERO because buggy firmware assumes ICM pages are
+	 * cleared, and subtle failures are seen if they aren't.
+	 */
+	page = alloc_pages(gfp_mask | __GFP_ZERO, order);
 	if (!page)
 		return -ENOMEM;
 

drivers/lguest/x86/core.c

@@ -176,7 +176,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	 * we set it now, so we can trap and pass that trap to the Guest if it
 	 * uses the FPU. */
 	if (cpu->ts)
-		lguest_set_ts();
+		unlazy_fpu(current);
 
 	/* SYSENTER is an optimized way of doing system calls.  We can't allow
 	 * it because it always jumps to privilege level 0.  A normal Guest
@@ -196,6 +196,10 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	 * trap made the switcher code come back, and an error code which some
 	 * traps set.  */
 
+	 /* Restore SYSENTER if it's supposed to be on. */
+	 if (boot_cpu_has(X86_FEATURE_SEP))
+		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
+
 	/* If the Guest page faulted, then the cr2 register will tell us the
 	 * bad virtual address.  We have to grab this now, because once we
 	 * re-enable interrupts an interrupt could fault and thus overwrite
@@ -203,13 +207,12 @@ void lguest_arch_run_guest(struct lg_cpu *cpu)
 	if (cpu->regs->trapnum == 14)
 		cpu->arch.last_pagefault = read_cr2();
 	/* Similarly, if we took a trap because the Guest used the FPU,
-	 * we have to restore the FPU it expects to see. */
+	 * we have to restore the FPU it expects to see.
+	 * math_state_restore() may sleep and we may even move off to
+	 * a different CPU. So all the critical stuff should be done
+	 * before this.  */
 	else if (cpu->regs->trapnum == 7)
 		math_state_restore();
-
-	/* Restore SYSENTER if it's supposed to be on. */
-	if (boot_cpu_has(X86_FEATURE_SEP))
-		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
 }
 
 /*H:130 Now we've examined the hypercall code; our Guest can make requests.

drivers/net/pppoe.c

@@ -942,7 +942,7 @@ static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock,
 	m->msg_namelen = 0;
 
 	if (skb) {
-		total_len = min(total_len, skb->len);
+		total_len = min_t(size_t, total_len, skb->len);
 		error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
 		if (error == 0)
 			error = total_len;

drivers/serial/bfin_5xx.c

@@ -49,6 +49,7 @@
 #define DMA_RX_YCOUNT		(PAGE_SIZE / DMA_RX_XCOUNT)
 
 #define DMA_RX_FLUSH_JIFFIES	(HZ / 50)
+#define CTS_CHECK_JIFFIES	(HZ / 50)
 
 #ifdef CONFIG_SERIAL_BFIN_DMA
 static void bfin_serial_dma_tx_chars(struct bfin_serial_port *uart);
@@ -290,11 +291,6 @@ static void bfin_serial_tx_chars(struct bfin_serial_port *uart)
 {
 	struct circ_buf *xmit = &uart->port.info->xmit;
 
-	if (uart->port.x_char) {
-		UART_PUT_CHAR(uart, uart->port.x_char);
-		uart->port.icount.tx++;
-		uart->port.x_char = 0;
-	}
 	/*
 	 * Check the modem control lines before
 	 * transmitting anything.
@@ -306,6 +302,12 @@ static void bfin_serial_tx_chars(struct bfin_serial_port *uart)
 		return;
 	}
 
+	if (uart->port.x_char) {
+		UART_PUT_CHAR(uart, uart->port.x_char);
+		uart->port.icount.tx++;
+		uart->port.x_char = 0;
+	}
+
 	while ((UART_GET_LSR(uart) & THRE) && xmit->tail != xmit->head) {
 		UART_PUT_CHAR(uart, xmit->buf[xmit->tail]);
 		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
@@ -345,15 +347,6 @@ static irqreturn_t bfin_serial_tx_int(int irq, void *dev_id)
 }
 #endif
 
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-static void bfin_serial_do_work(struct work_struct *work)
-{
-	struct bfin_serial_port *uart = container_of(work, struct bfin_serial_port, cts_workqueue);
-
-	bfin_serial_mctrl_check(uart);
-}
-#endif
-
 #ifdef CONFIG_SERIAL_BFIN_DMA
 static void bfin_serial_dma_tx_chars(struct bfin_serial_port *uart)
 {
@@ -361,6 +354,12 @@ static void bfin_serial_dma_tx_chars(struct bfin_serial_port *uart)
 
 	uart->tx_done = 0;
 
+	/*
+	 * Check the modem control lines before
+	 * transmitting anything.
+	 */
+	bfin_serial_mctrl_check(uart);
+
 	if (uart_circ_empty(xmit) || uart_tx_stopped(&uart->port)) {
 		uart->tx_count = 0;
 		uart->tx_done = 1;
@@ -373,12 +372,6 @@ static void bfin_serial_dma_tx_chars(struct bfin_serial_port *uart)
 		uart->port.x_char = 0;
 	}
 
-	/*
-	 * Check the modem control lines before
-	 * transmitting anything.
-	 */
-	bfin_serial_mctrl_check(uart);
-
 	uart->tx_count = CIRC_CNT(xmit->head, xmit->tail, UART_XMIT_SIZE);
 	if (uart->tx_count > (UART_XMIT_SIZE - xmit->tail))
 		uart->tx_count = UART_XMIT_SIZE - xmit->tail;
@@ -565,7 +558,10 @@ static void bfin_serial_mctrl_check(struct bfin_serial_port *uart)
 	uart_handle_cts_change(&uart->port, status & TIOCM_CTS);
 	if (!(status & TIOCM_CTS)) {
 		tty->hw_stopped = 1;
-		schedule_work(&uart->cts_workqueue);
+		uart->cts_timer.data = (unsigned long)(uart);
+		uart->cts_timer.function = (void *)bfin_serial_mctrl_check;
+		uart->cts_timer.expires = jiffies + CTS_CHECK_JIFFIES;
+		add_timer(&(uart->cts_timer));
 	} else {
 		tty->hw_stopped = 0;
 	}
@@ -885,7 +881,7 @@ static void __init bfin_serial_init_ports(void)
 		init_timer(&(bfin_serial_ports[i].rx_dma_timer));
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-		INIT_WORK(&bfin_serial_ports[i].cts_workqueue, bfin_serial_do_work);
+		init_timer(&(bfin_serial_ports[i].cts_timer));
 		bfin_serial_ports[i].cts_pin	    =
 			bfin_serial_resource[i].uart_cts_pin;
 		bfin_serial_ports[i].rts_pin	    =

drivers/watchdog/Makefile

@@ -68,7 +68,6 @@ obj-$(CONFIG_WAFER_WDT) += wafer5823wdt.o
 obj-$(CONFIG_I6300ESB_WDT) += i6300esb.o
 obj-$(CONFIG_ITCO_WDT) += iTCO_wdt.o iTCO_vendor_support.o
 obj-$(CONFIG_IT8712F_WDT) += it8712f_wdt.o
-CFLAGS_hpwdt.o += -O
 obj-$(CONFIG_HP_WATCHDOG) += hpwdt.o
 obj-$(CONFIG_SC1200_WDT) += sc1200wdt.o
 obj-$(CONFIG_SCx200_WDT) += scx200_wdt.o

drivers/watchdog/hpwdt.c

@@ -140,15 +140,17 @@ static struct pci_device_id hpwdt_devices[] = {
 };
 MODULE_DEVICE_TABLE(pci, hpwdt_devices);
 
+extern asmlinkage void asminline_call(struct cmn_registers *pi86Regs, unsigned long *pRomEntry);
+
 #ifndef CONFIG_X86_64
 /* --32 Bit Bios------------------------------------------------------------ */
 
 #define HPWDT_ARCH	32
 
-asmlinkage void asminline_call(struct cmn_registers *pi86Regs,
+asm(".text                          \n\t"
-			       unsigned long *pRomEntry)
+    ".align 4                       \n"
-{
+    "asminline_call:                \n\t"
-	asm("pushl       %ebp               \n\t"
+    "pushl       %ebp               \n\t"
     "movl        %esp, %ebp         \n\t"
     "pusha                          \n\t"
     "pushf                          \n\t"
@@ -181,8 +183,10 @@ asmlinkage void asminline_call(struct cmn_registers *pi86Regs,
     "pop         %es                \n\t"
     "popf                           \n\t"
     "popa                           \n\t"
-	    "leave                          \n\t" "ret");
+    "leave                          \n\t"
-}
+    "ret                            \n\t"
+    ".previous");
+
 
 /*
  *	cru_detect
@@ -333,10 +337,10 @@ static int __devinit detect_cru_service(void)
 
 #define HPWDT_ARCH	64
 
-asmlinkage void asminline_call(struct cmn_registers *pi86Regs,
+asm(".text                      \n\t"
-			       unsigned long *pRomEntry)
+    ".align 4                   \n"
-{
+    "asminline_call:            \n\t"
-	asm("pushq      %rbp            \n\t"
+    "pushq      %rbp            \n\t"
     "movq       %rsp, %rbp      \n\t"
     "pushq      %rax            \n\t"
     "pushq      %rbx            \n\t"
@@ -368,8 +372,9 @@ asmlinkage void asminline_call(struct cmn_registers *pi86Regs,
     "popq       %rdx            \n\t"
     "popq       %rbx            \n\t"
     "popq       %rax            \n\t"
-	    "leave                      \n\t" "ret");
+    "leave                      \n\t"
-}
+    "ret                        \n\t"
+    ".previous");
 
 /*
  *	dmi_find_cru

drivers/xen/events.c

@@ -529,7 +529,7 @@ void xen_evtchn_do_upcall(struct pt_regs *regs)
 
 #ifndef CONFIG_X86 /* No need for a barrier -- XCHG is a barrier on x86. */
 		/* Clear master flag /before/ clearing selector flag. */
-		rmb();
+		wmb();
 #endif
 		pending_words = xchg(&vcpu_info->evtchn_pending_sel, 0);
 		while (pending_words != 0) {

fs/ext4/resize.c

@@ -855,7 +855,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	 */
 
 	/* Update group descriptor block for new group */
-	gdp = (struct ext4_group_desc *)primary->b_data + gdb_off;
+	gdp = (struct ext4_group_desc *)((char *)primary->b_data +
+					 gdb_off * EXT4_DESC_SIZE(sb));
 
 	ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
 	ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */

fs/gfs2/bmap.c

@@ -246,15 +246,11 @@ static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
 
 }
 
-static inline unsigned int zero_metapath_length(const struct metapath *mp,
+static inline unsigned int metapath_branch_start(const struct metapath *mp)
-						unsigned height)
 {
-	unsigned int i;
+	if (mp->mp_list[0] == 0)
-	for (i = 0; i < height - 1; i++) {
+		return 2;
-		if (mp->mp_list[i] != 0)
+	return 1;
-			return i;
-	}
-	return height;
 }
 
 /**
@@ -436,7 +432,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct buffer_head *dibh = mp->mp_bh[0];
 	u64 bn, dblock = 0;
-	unsigned n, i, blks, alloced = 0, iblks = 0, zmpl = 0;
+	unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
 	unsigned dblks = 0;
 	unsigned ptrs_per_blk;
 	const unsigned end_of_metadata = height - 1;
@@ -471,9 +467,8 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 			/* Building up tree height */
 			state = ALLOC_GROW_HEIGHT;
 			iblks = height - ip->i_height;
-			zmpl = zero_metapath_length(mp, height);
+			branch_start = metapath_branch_start(mp);
-			iblks -= zmpl;
+			iblks += (height - branch_start);
-			iblks += height;
 		}
 	}
 
@@ -509,13 +504,13 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 					sizeof(struct gfs2_meta_header));
 				*ptr = zero_bn;
 				state = ALLOC_GROW_DEPTH;
-				for(i = zmpl; i < height; i++) {
+				for(i = branch_start; i < height; i++) {
 					if (mp->mp_bh[i] == NULL)
 						break;
 					brelse(mp->mp_bh[i]);
 					mp->mp_bh[i] = NULL;
 				}
-				i = zmpl;
+				i = branch_start;
 			}
 			if (n == 0)
 				break;

fs/gfs2/rgrp.c

@@ -195,7 +195,7 @@ ulong_aligned:
 	   depending on architecture.  I've experimented with several ways
 	   of writing this section such as using an else before the goto
 	   but this one seems to be the fastest. */
-	while ((unsigned char *)plong < end - 1) {
+	while ((unsigned char *)plong < end - sizeof(unsigned long)) {
 		prefetch(plong + 1);
 		if (((*plong) & LBITMASK) != lskipval)
 			break;

fs/nfs/mount_clnt.c

@@ -130,10 +130,11 @@ static int xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p,
 				struct mnt_fhstatus *res)
 {
 	struct nfs_fh *fh = res->fh;
+	unsigned size;
 
 	if ((res->status = ntohl(*p++)) == 0) {
-		int size = ntohl(*p++);
+		size = ntohl(*p++);
-		if (size <= NFS3_FHSIZE) {
+		if (size <= NFS3_FHSIZE && size != 0) {
 			fh->size = size;
 			memcpy(fh->data, p, size);
 		} else

fs/nfs/super.c

@@ -1216,8 +1216,6 @@ static int nfs_validate_mount_data(void *options,
 {
 	struct nfs_mount_data *data = (struct nfs_mount_data *)options;
 
-	memset(args, 0, sizeof(*args));
-
 	if (data == NULL)
 		goto out_no_data;
 
@@ -1251,13 +1249,13 @@ static int nfs_validate_mount_data(void *options,
 	case 5:
 		memset(data->context, 0, sizeof(data->context));
 	case 6:
-		if (data->flags & NFS_MOUNT_VER3)
+		if (data->flags & NFS_MOUNT_VER3) {
+			if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
+				goto out_invalid_fh;
 			mntfh->size = data->root.size;
-		else
+		} else
 			mntfh->size = NFS2_FHSIZE;
 
-		if (mntfh->size > sizeof(mntfh->data))
-			goto out_invalid_fh;
 
 		memcpy(mntfh->data, data->root.data, mntfh->size);
 		if (mntfh->size < sizeof(mntfh->data))
@@ -1585,24 +1583,29 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 {
 	struct nfs_server *server = NULL;
 	struct super_block *s;
-	struct nfs_fh mntfh;
+	struct nfs_parsed_mount_data *data;
-	struct nfs_parsed_mount_data data;
+	struct nfs_fh *mntfh;
 	struct dentry *mntroot;
 	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
 	struct nfs_sb_mountdata sb_mntdata = {
 		.mntflags = flags,
 	};
-	int error;
+	int error = -ENOMEM;
 
-	security_init_mnt_opts(&data.lsm_opts);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL);
+	if (data == NULL || mntfh == NULL)
+		goto out_free_fh;
+
+	security_init_mnt_opts(&data->lsm_opts);
 
 	/* Validate the mount data */
-	error = nfs_validate_mount_data(raw_data, &data, &mntfh, dev_name);
+	error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name);
 	if (error < 0)
 		goto out;
 
 	/* Get a volume representation */
-	server = nfs_create_server(&data, &mntfh);
+	server = nfs_create_server(data, mntfh);
 	if (IS_ERR(server)) {
 		error = PTR_ERR(server);
 		goto out;
@@ -1630,16 +1633,16 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 
 	if (!s->s_root) {
 		/* initial superblock/root creation */
-		nfs_fill_super(s, &data);
+		nfs_fill_super(s, data);
 	}
 
-	mntroot = nfs_get_root(s, &mntfh);
+	mntroot = nfs_get_root(s, mntfh);
 	if (IS_ERR(mntroot)) {
 		error = PTR_ERR(mntroot);
 		goto error_splat_super;
 	}
 
-	error = security_sb_set_mnt_opts(s, &data.lsm_opts);
+	error = security_sb_set_mnt_opts(s, &data->lsm_opts);
 	if (error)
 		goto error_splat_root;
 
@@ -1649,9 +1652,12 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 	error = 0;
 
 out:
-	kfree(data.nfs_server.hostname);
+	kfree(data->nfs_server.hostname);
-	kfree(data.mount_server.hostname);
+	kfree(data->mount_server.hostname);
-	security_free_mnt_opts(&data.lsm_opts);
+	security_free_mnt_opts(&data->lsm_opts);
+out_free_fh:
+	kfree(mntfh);
+	kfree(data);
 	return error;
 
 out_err_nosb:
@@ -1800,8 +1806,6 @@ static int nfs4_validate_mount_data(void *options,
 	struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
 	char *c;
 
-	memset(args, 0, sizeof(*args));
-
 	if (data == NULL)
 		goto out_no_data;
 
@@ -1959,26 +1963,31 @@ out_no_client_address:
 static int nfs4_get_sb(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
 {
-	struct nfs_parsed_mount_data data;
+	struct nfs_parsed_mount_data *data;
 	struct super_block *s;
 	struct nfs_server *server;
-	struct nfs_fh mntfh;
+	struct nfs_fh *mntfh;
 	struct dentry *mntroot;
 	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
 	struct nfs_sb_mountdata sb_mntdata = {
 		.mntflags = flags,
 	};
-	int error;
+	int error = -ENOMEM;
 
-	security_init_mnt_opts(&data.lsm_opts);
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	mntfh = kzalloc(sizeof(*mntfh), GFP_KERNEL);
+	if (data == NULL || mntfh == NULL)
+		goto out_free_fh;
+
+	security_init_mnt_opts(&data->lsm_opts);
 
 	/* Validate the mount data */
-	error = nfs4_validate_mount_data(raw_data, &data, dev_name);
+	error = nfs4_validate_mount_data(raw_data, data, dev_name);
 	if (error < 0)
 		goto out;
 
 	/* Get a volume representation */
-	server = nfs4_create_server(&data, &mntfh);
+	server = nfs4_create_server(data, mntfh);
 	if (IS_ERR(server)) {
 		error = PTR_ERR(server);
 		goto out;
@@ -2009,13 +2018,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 		nfs4_fill_super(s);
 	}
 
-	mntroot = nfs4_get_root(s, &mntfh);
+	mntroot = nfs4_get_root(s, mntfh);
 	if (IS_ERR(mntroot)) {
 		error = PTR_ERR(mntroot);
 		goto error_splat_super;
 	}
 
-	error = security_sb_set_mnt_opts(s, &data.lsm_opts);
+	error = security_sb_set_mnt_opts(s, &data->lsm_opts);
 	if (error)
 		goto error_splat_root;
 
@@ -2025,10 +2034,13 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 	error = 0;
 
 out:
-	kfree(data.client_address);
+	kfree(data->client_address);
-	kfree(data.nfs_server.export_path);
+	kfree(data->nfs_server.export_path);
-	kfree(data.nfs_server.hostname);
+	kfree(data->nfs_server.hostname);
-	security_free_mnt_opts(&data.lsm_opts);
+	security_free_mnt_opts(&data->lsm_opts);
+out_free_fh:
+	kfree(mntfh);
+	kfree(data);
 	return error;
 
 out_free:

fs/nfs/write.c

@@ -739,12 +739,13 @@ int nfs_updatepage(struct file *file, struct page *page,
 	}
 
 	status = nfs_writepage_setup(ctx, page, offset, count);
+	if (status < 0)
+		nfs_set_pageerror(page);
+	else
 		__set_page_dirty_nobuffers(page);
 
         dprintk("NFS:      nfs_updatepage returns %d (isize %Ld)\n",
 			status, (long long)i_size_read(inode));
-	if (status < 0)
-		nfs_set_pageerror(page);
 	return status;
 }
 

fs/select.c

@@ -249,7 +249,6 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
 						retval++;
 					}
 				}
-				cond_resched();
 			}
 			if (res_in)
 				*rinp = res_in;
@@ -257,6 +256,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
 				*routp = res_out;
 			if (res_ex)
 				*rexp = res_ex;
+			cond_resched();
 		}
 		wait = NULL;
 		if (retval || !*timeout || signal_pending(current))

include/asm-alpha/core_mcpcia.h

@@ -261,7 +261,7 @@ struct el_MCPCIA_uncorrected_frame_mcheck {
 	}
 #endif
 
-static inline int __mcpcia_is_mmio(unsigned long addr)
+extern inline int __mcpcia_is_mmio(unsigned long addr)
 {
 	return (addr & 0x80000000UL) == 0;
 }

include/asm-alpha/core_t2.h

@@ -356,13 +356,13 @@ struct el_t2_frame_corrected {
 #define vip	volatile int *
 #define vuip	volatile unsigned int *
 
-static inline u8 t2_inb(unsigned long addr)
+extern inline u8 t2_inb(unsigned long addr)
 {
 	long result = *(vip) ((addr << 5) + T2_IO + 0x00);
 	return __kernel_extbl(result, addr & 3);
 }
 
-static inline void t2_outb(u8 b, unsigned long addr)
+extern inline void t2_outb(u8 b, unsigned long addr)
 {
 	unsigned long w;
 
@@ -371,13 +371,13 @@ static inline void t2_outb(u8 b, unsigned long addr)
 	mb();
 }
 
-static inline u16 t2_inw(unsigned long addr)
+extern inline u16 t2_inw(unsigned long addr)
 {
 	long result = *(vip) ((addr << 5) + T2_IO + 0x08);
 	return __kernel_extwl(result, addr & 3);
 }
 
-static inline void t2_outw(u16 b, unsigned long addr)
+extern inline void t2_outw(u16 b, unsigned long addr)
 {
 	unsigned long w;
 
@@ -386,12 +386,12 @@ static inline void t2_outw(u16 b, unsigned long addr)
 	mb();
 }
 
-static inline u32 t2_inl(unsigned long addr)
+extern inline u32 t2_inl(unsigned long addr)
 {
 	return *(vuip) ((addr << 5) + T2_IO + 0x18);
 }
 
-static inline void t2_outl(u32 b, unsigned long addr)
+extern inline void t2_outl(u32 b, unsigned long addr)
 {
 	*(vuip) ((addr << 5) + T2_IO + 0x18) = b;
 	mb();
@@ -435,7 +435,7 @@ static inline void t2_outl(u32 b, unsigned long addr)
 	set_hae(msb); \
 }
 
-static DEFINE_SPINLOCK(t2_hae_lock);
+extern spinlock_t t2_hae_lock;
 
 /*
  * NOTE: take T2_DENSE_MEM off in each readX/writeX routine, since

include/asm-alpha/io.h

@@ -35,7 +35,7 @@
  * register not being up-to-date with respect to the hardware
  * value.
  */
-static inline void __set_hae(unsigned long new_hae)
+extern inline void __set_hae(unsigned long new_hae)
 {
 	unsigned long flags;
 	local_irq_save(flags);
@@ -49,7 +49,7 @@ static inline void __set_hae(unsigned long new_hae)
 	local_irq_restore(flags);
 }
 
-static inline void set_hae(unsigned long new_hae)
+extern inline void set_hae(unsigned long new_hae)
 {
 	if (new_hae != alpha_mv.hae_cache)
 		__set_hae(new_hae);
@@ -176,7 +176,7 @@ REMAP2(u64, writeq, volatile)
 #undef REMAP1
 #undef REMAP2
 
-static inline void __iomem *generic_ioportmap(unsigned long a)
+extern inline void __iomem *generic_ioportmap(unsigned long a)
 {
 	return alpha_mv.mv_ioportmap(a);
 }

include/asm-alpha/mmu_context.h

@@ -23,7 +23,7 @@
 #endif
 
 
-extern inline unsigned long
+static inline unsigned long
 __reload_thread(struct pcb_struct *pcb)
 {
 	register unsigned long a0 __asm__("$16");
@@ -114,7 +114,7 @@ extern unsigned long last_asn;
 #define __MMU_EXTERN_INLINE
 #endif
 
-static inline unsigned long
+extern inline unsigned long
 __get_new_mm_context(struct mm_struct *mm, long cpu)
 {
 	unsigned long asn = cpu_last_asn(cpu);
@@ -226,7 +226,7 @@ ev4_activate_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm)
 # endif
 #endif
 
-extern inline int
+static inline int
 init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
 	int i;

include/asm-alpha/percpu.h

@@ -1,6 +1,78 @@
 #ifndef __ALPHA_PERCPU_H
 #define __ALPHA_PERCPU_H
+#include <linux/compiler.h>
+#include <linux/threads.h>
 
-#include <asm-generic/percpu.h>
+/*
+ * Determine the real variable name from the name visible in the
+ * kernel sources.
+ */
+#define per_cpu_var(var) per_cpu__##var
+
+#ifdef CONFIG_SMP
+
+/*
+ * per_cpu_offset() is the offset that has to be added to a
+ * percpu variable to get to the instance for a certain processor.
+ */
+extern unsigned long __per_cpu_offset[NR_CPUS];
+
+#define per_cpu_offset(x) (__per_cpu_offset[x])
+
+#define __my_cpu_offset per_cpu_offset(raw_smp_processor_id())
+#ifdef CONFIG_DEBUG_PREEMPT
+#define my_cpu_offset per_cpu_offset(smp_processor_id())
+#else
+#define my_cpu_offset __my_cpu_offset
+#endif
+
+#ifndef MODULE
+#define SHIFT_PERCPU_PTR(var, offset) RELOC_HIDE(&per_cpu_var(var), (offset))
+#define PER_CPU_ATTRIBUTES
+#else
+/*
+ * To calculate addresses of locally defined variables, GCC uses 32-bit
+ * displacement from the GP. Which doesn't work for per cpu variables in
+ * modules, as an offset to the kernel per cpu area is way above 4G.
+ *
+ * This forces allocation of a GOT entry for per cpu variable using
+ * ldq instruction with a 'literal' relocation.
+ */
+#define SHIFT_PERCPU_PTR(var, offset) ({		\
+	extern int simple_identifier_##var(void);	\
+	unsigned long __ptr, tmp_gp;			\
+	asm (  "br	%1, 1f		  	      \n\
+	1:	ldgp	%1, 0(%1)	    	      \n\
+		ldq %0, per_cpu__" #var"(%1)\t!literal"		\
+		: "=&r"(__ptr), "=&r"(tmp_gp));		\
+	(typeof(&per_cpu_var(var)))(__ptr + (offset)); })
+
+#define PER_CPU_ATTRIBUTES	__used
+
+#endif /* MODULE */
+
+/*
+ * A percpu variable may point to a discarded regions. The following are
+ * established ways to produce a usable pointer from the percpu variable
+ * offset.
+ */
+#define per_cpu(var, cpu) \
+	(*SHIFT_PERCPU_PTR(var, per_cpu_offset(cpu)))
+#define __get_cpu_var(var) \
+	(*SHIFT_PERCPU_PTR(var, my_cpu_offset))
+#define __raw_get_cpu_var(var) \
+	(*SHIFT_PERCPU_PTR(var, __my_cpu_offset))
+
+#else /* ! SMP */
+
+#define per_cpu(var, cpu)		(*((void)(cpu), &per_cpu_var(var)))
+#define __get_cpu_var(var)		per_cpu_var(var)
+#define __raw_get_cpu_var(var)		per_cpu_var(var)
+
+#define PER_CPU_ATTRIBUTES
+
+#endif /* SMP */
+
+#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu_var(name)
 
 #endif /* __ALPHA_PERCPU_H */

include/asm-alpha/system.h

@@ -184,7 +184,7 @@ enum amask_enum {
    __amask; })
 
 #define __CALL_PAL_R0(NAME, TYPE)				\
-static inline TYPE NAME(void)					\
+extern inline TYPE NAME(void)					\
 {								\
 	register TYPE __r0 __asm__("$0");			\
 	__asm__ __volatile__(					\
@@ -196,7 +196,7 @@ static inline TYPE NAME(void)					\
 }
 
 #define __CALL_PAL_W1(NAME, TYPE0)				\
-static inline void NAME(TYPE0 arg0)				\
+extern inline void NAME(TYPE0 arg0)				\
 {								\
 	register TYPE0 __r16 __asm__("$16") = arg0;		\
 	__asm__ __volatile__(					\
@@ -207,7 +207,7 @@ static inline void NAME(TYPE0 arg0)				\
 }
 
 #define __CALL_PAL_W2(NAME, TYPE0, TYPE1)			\
-static inline void NAME(TYPE0 arg0, TYPE1 arg1)			\
+extern inline void NAME(TYPE0 arg0, TYPE1 arg1)			\
 {								\
 	register TYPE0 __r16 __asm__("$16") = arg0;		\
 	register TYPE1 __r17 __asm__("$17") = arg1;		\
@@ -219,7 +219,7 @@ static inline void NAME(TYPE0 arg0, TYPE1 arg1)			\
 }
 
 #define __CALL_PAL_RW1(NAME, RTYPE, TYPE0)			\
-static inline RTYPE NAME(TYPE0 arg0)				\
+extern inline RTYPE NAME(TYPE0 arg0)				\
 {								\
 	register RTYPE __r0 __asm__("$0");			\
 	register TYPE0 __r16 __asm__("$16") = arg0;		\
@@ -232,7 +232,7 @@ static inline RTYPE NAME(TYPE0 arg0)				\
 }
 
 #define __CALL_PAL_RW2(NAME, RTYPE, TYPE0, TYPE1)		\
-static inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1)		\
+extern inline RTYPE NAME(TYPE0 arg0, TYPE1 arg1)		\
 {								\
 	register RTYPE __r0 __asm__("$0");			\
 	register TYPE0 __r16 __asm__("$16") = arg0;		\

include/asm-alpha/vga.h

@@ -13,7 +13,7 @@
 #define VT_BUF_HAVE_MEMSETW
 #define VT_BUF_HAVE_MEMCPYW
 
-extern inline void scr_writew(u16 val, volatile u16 *addr)
+static inline void scr_writew(u16 val, volatile u16 *addr)
 {
 	if (__is_ioaddr(addr))
 		__raw_writew(val, (volatile u16 __iomem *) addr);
@@ -21,7 +21,7 @@ extern inline void scr_writew(u16 val, volatile u16 *addr)
 		*addr = val;
 }
 
-extern inline u16 scr_readw(volatile const u16 *addr)
+static inline u16 scr_readw(volatile const u16 *addr)
 {
 	if (__is_ioaddr(addr))
 		return __raw_readw((volatile const u16 __iomem *) addr);
@@ -29,7 +29,7 @@ extern inline u16 scr_readw(volatile const u16 *addr)
 		return *addr;
 }
 
-extern inline void scr_memsetw(u16 *s, u16 c, unsigned int count)
+static inline void scr_memsetw(u16 *s, u16 c, unsigned int count)
 {
 	if (__is_ioaddr(s))
 		memsetw_io((u16 __iomem *) s, c, count);

include/asm-blackfin/mach-bf527/bfin_serial_5xx.h

@@ -96,7 +96,7 @@ struct bfin_serial_port {
 	struct work_struct tx_dma_workqueue;
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	struct work_struct cts_workqueue;
+	struct timer_list cts_timer;
 	int cts_pin;
 	int rts_pin;
 #endif

include/asm-blackfin/mach-bf533/bfin_serial_5xx.h

@@ -88,7 +88,7 @@ struct bfin_serial_port {
 # endif
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	struct work_struct 	cts_workqueue;
+	struct timer_list       cts_timer;
 	int			cts_pin;
 	int			rts_pin;
 #endif

include/asm-blackfin/mach-bf537/bfin_serial_5xx.h

@@ -96,7 +96,7 @@ struct bfin_serial_port {
 	struct work_struct	tx_dma_workqueue;
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	struct work_struct 	cts_workqueue;
+	struct timer_list 	cts_timer;
 	int		cts_pin;
 	int 		rts_pin;
 #endif

include/asm-blackfin/mach-bf548/bfin_serial_5xx.h

@@ -99,7 +99,7 @@ struct bfin_serial_port {
 	struct work_struct	tx_dma_workqueue;
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	struct work_struct 	cts_workqueue;
+	struct timer_list 	cts_timer;
 	int		cts_pin;
 	int 		rts_pin;
 #endif
@@ -187,7 +187,7 @@ static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 
 #ifdef CONFIG_BFIN_UART1_CTSRTS
 	peripheral_request(P_UART1_RTS, DRIVER_NAME);
-	peripheral_request(P_UART1_CTS DRIVER_NAME);
+	peripheral_request(P_UART1_CTS, DRIVER_NAME);
 #endif
 #endif
 
@@ -202,7 +202,7 @@ static void bfin_serial_hw_init(struct bfin_serial_port *uart)
 
 #ifdef CONFIG_BFIN_UART3_CTSRTS
 	peripheral_request(P_UART3_RTS, DRIVER_NAME);
-	peripheral_request(P_UART3_CTS DRIVER_NAME);
+	peripheral_request(P_UART3_CTS, DRIVER_NAME);
 #endif
 #endif
 	SSYNC();

include/asm-blackfin/mach-bf561/bfin_serial_5xx.h

@@ -88,7 +88,7 @@ struct bfin_serial_port {
 # endif
 #endif
 #ifdef CONFIG_SERIAL_BFIN_CTSRTS
-	struct work_struct 	cts_workqueue;
+	struct timer_list       cts_timer;
 	int			cts_pin;
 	int			rts_pin;
 #endif